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

Dataset: Open Web Text

Neuron 617 in Layer 2

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: 2.0986. Min Range: -2.0986

Max Act: 2.0976. Min Act: -0.1700

Data Index: 7665212 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0895. Min Act: -0.1700

Data Index: 5767911 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0986. Min Act: -0.1700

Data Index: 8325897 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0887. Min Act: -0.1700

Data Index: 1768374 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0706. Min Act: -0.1700

Data Index: 8781322 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0659. Min Act: -0.1700

Data Index: 4492572 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0483. Min Act: -0.1700

Data Index: 6690110 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0778. Min Act: -0.1700

Data Index: 1606114 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0631. Min Act: -0.1700

Data Index: 2836776 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0697. Min Act: -0.1700

Data Index: 3223686 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0729. Min Act: -0.1700

Data Index: 6307346 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0629. Min Act: -0.1700

Data Index: 4811569 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0728. Min Act: -0.1700

Data Index: 5915231 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0361. Min Act: -0.1700

Data Index: 8670262 (Open Web Text)

Max Activating Token Index: 94

Text #14

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0496. Min Act: -0.1700

Data Index: 5996063 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0700. Min Act: -0.1700

Data Index: 8441031 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0334. Min Act: -0.1700

Data Index: 7905576 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0464. Min Act: -0.1700

Data Index: 7698067 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0158. Min Act: -0.1700

Data Index: 7759014 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0396. Min Act: -0.1700

Data Index: 6888385 (Open Web Text)

Max Activating Token Index: 147