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

Dataset: Open Web Text

Neuron 64 in Layer 0

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: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 3878062 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 2425717 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 6992483 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 3026720 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 3687996 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 6563632 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 7164050 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 2734047 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 7580465 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 8191946 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 5794695 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 8131164 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 8050580 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 4781379 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 267565 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 6856286 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3006. Min Act: -0.1700

Data Index: 4316744 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2965. Min Act: -0.1700

Data Index: 2868247 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2820. Min Act: -0.1700

Data Index: 1561972 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2891. Min Act: -0.1700

Data Index: 9416 (Open Web Text)

Max Activating Token Index: 3