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

Dataset: Open Web Text

Neuron 271 in Layer 5

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: 4.5914. Min Range: -4.5914

Max Act: 4.5914. Min Act: -0.1700

Data Index: 7625410 (Open Web Text)

Max Activating Token Index: 491

Text #1

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.3634. Min Act: -0.1700

Data Index: 8645837 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.2972. Min Act: -0.1700

Data Index: 6385496 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.2684. Min Act: -0.1700

Data Index: 1239753 (Open Web Text)

Max Activating Token Index: 939

Text #4

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.2610. Min Act: -0.1700

Data Index: 3585361 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.2583. Min Act: -0.1700

Data Index: 5079868 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.2237. Min Act: -0.1700

Data Index: 8649293 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1968. Min Act: -0.1700

Data Index: 1447509 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1627. Min Act: -0.1700

Data Index: 4829624 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1334. Min Act: -0.1700

Data Index: 2217944 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1104. Min Act: -0.1700

Data Index: 663129 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.0878. Min Act: -0.1700

Data Index: 3316302 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1154. Min Act: -0.1700

Data Index: 6850472 (Open Web Text)

Max Activating Token Index: 647

Text #13

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.0717. Min Act: -0.1700

Data Index: 1078117 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1286. Min Act: -0.1700

Data Index: 519322 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1063. Min Act: -0.1700

Data Index: 8265774 (Open Web Text)

Max Activating Token Index: 925

Text #16

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.0923. Min Act: -0.1700

Data Index: 3107008 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.1149. Min Act: -0.1700

Data Index: 3582190 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.0877. Min Act: -0.1700

Data Index: 5056606 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.0921. Min Act: -0.1700

Data Index: 607867 (Open Web Text)

Max Activating Token Index: 734