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

Dataset: Open Web Text

Neuron 1221 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: 3.8036. Min Range: -3.8036

Max Act: 3.8036. Min Act: -0.1700

Data Index: 5496513 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.7678. Min Act: -0.1700

Data Index: 7608491 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.7328. Min Act: -0.1700

Data Index: 1670488 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.7334. Min Act: -0.1700

Data Index: 3150859 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.7003. Min Act: -0.1700

Data Index: 3961434 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.7084. Min Act: -0.1700

Data Index: 6454809 (Open Web Text)

Max Activating Token Index: 266

Text #6

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6907. Min Act: -0.1700

Data Index: 2818716 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6813. Min Act: -0.1700

Data Index: 3727499 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6668. Min Act: -0.1700

Data Index: 4617627 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6496. Min Act: -0.1700

Data Index: 493523 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6514. Min Act: -0.1700

Data Index: 4925921 (Open Web Text)

Max Activating Token Index: 514

Text #11

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6538. Min Act: -0.1700

Data Index: 5024630 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6605. Min Act: -0.1700

Data Index: 7194541 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6519. Min Act: -0.1700

Data Index: 2883186 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6581. Min Act: -0.1700

Data Index: 7204772 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6796. Min Act: -0.1700

Data Index: 3795695 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6544. Min Act: -0.1700

Data Index: 3362571 (Open Web Text)

Max Activating Token Index: 733

Text #17

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6571. Min Act: -0.1700

Data Index: 7244170 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6742. Min Act: -0.1700

Data Index: 7498937 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 3.8036. Min Range: -3.8036

Max Act: 3.6793. Min Act: -0.1700

Data Index: 32484 (Open Web Text)

Max Activating Token Index: 596