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

Dataset: Open Web Text

Neuron 3068 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: 5.8939. Min Range: -5.8939

Max Act: 5.8939. Min Act: -0.1700

Data Index: 1251405 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 5.8939. Min Range: -5.8939

Max Act: 5.7106. Min Act: -0.1700

Data Index: 1133504 (Open Web Text)

Max Activating Token Index: 159

Text #2

Max Range: 5.8939. Min Range: -5.8939

Max Act: 5.6100. Min Act: -0.1700

Data Index: 1251409 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 5.8939. Min Range: -5.8939

Max Act: 5.5626. Min Act: -0.1700

Data Index: 1251402 (Open Web Text)

Max Activating Token Index: 727

Text #4

Max Range: 5.8939. Min Range: -5.8939

Max Act: 5.1124. Min Act: -0.1700

Data Index: 4596840 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.9464. Min Act: -0.1700

Data Index: 1211428 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.8147. Min Act: -0.1700

Data Index: 2688351 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.7512. Min Act: -0.1700

Data Index: 1251408 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.7403. Min Act: -0.1700

Data Index: 7783831 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.6814. Min Act: -0.1700

Data Index: 8786255 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5894. Min Act: -0.1699

Data Index: 4552371 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5604. Min Act: -0.1700

Data Index: 3187211 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5767. Min Act: -0.1700

Data Index: 2577517 (Open Web Text)

Max Activating Token Index: 750

Text #13

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5775. Min Act: -0.1700

Data Index: 1251403 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5223. Min Act: -0.1700

Data Index: 553273 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.5254. Min Act: -0.1700

Data Index: 1251410 (Open Web Text)

Max Activating Token Index: 744

Text #16

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.4164. Min Act: -0.1700

Data Index: 6677223 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.4496. Min Act: -0.1700

Data Index: 3544425 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.4203. Min Act: -0.1700

Data Index: 4596841 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 5.8939. Min Range: -5.8939

Max Act: 4.4138. Min Act: -0.1700

Data Index: 1251407 (Open Web Text)

Max Activating Token Index: 259