< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 531 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 4149458 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 847642 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 7087283 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 843291 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 3969579 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 4352591 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 5619302 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 3453808 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 8287900 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 5394063 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 7999643 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 706872 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 5356818 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.6602. Min Act: -0.1700

Data Index: 4147169 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.4950. Min Act: -0.1700

Data Index: 6388166 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.5027. Min Act: -0.1700

Data Index: 2903288 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.4605. Min Act: -0.1700

Data Index: 324895 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.4605. Min Act: -0.1700

Data Index: 7317416 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.4605. Min Act: -0.1700

Data Index: 4963747 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.6602. Min Range: -4.6602

Max Act: 4.4605. Min Act: -0.1700

Data Index: 2910700 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19