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

Dataset: Open Web Text

Neuron 614 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: 5.3127. Min Range: -5.3127

Max Act: 5.3127. Min Act: -0.1700

Data Index: 6416755 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.2176. Min Act: -0.1700

Data Index: 1333499 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1867. Min Act: -0.1700

Data Index: 6155629 (Open Web Text)

Max Activating Token Index: 1012

Text #3

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1466. Min Act: -0.1700

Data Index: 2949333 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1386. Min Act: -0.1700

Data Index: 5568216 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1445. Min Act: -0.1700

Data Index: 762259 (Open Web Text)

Max Activating Token Index: 558

Text #6

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1207. Min Act: -0.1700

Data Index: 5552803 (Open Web Text)

Max Activating Token Index: 906

Text #7

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0929. Min Act: -0.1700

Data Index: 6797007 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1107. Min Act: -0.1700

Data Index: 2127647 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1166. Min Act: -0.1700

Data Index: 622723 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0763. Min Act: -0.1700

Data Index: 8315762 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1162. Min Act: -0.1700

Data Index: 3060302 (Open Web Text)

Max Activating Token Index: 549

Text #12

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0763. Min Act: -0.1700

Data Index: 6155630 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0896. Min Act: -0.1700

Data Index: 2485108 (Open Web Text)

Max Activating Token Index: 943

Text #14

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0643. Min Act: -0.1700

Data Index: 6208587 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0834. Min Act: -0.1700

Data Index: 7304365 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0505. Min Act: -0.1700

Data Index: 5274647 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0713. Min Act: -0.1700

Data Index: 5334448 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0580. Min Act: -0.1700

Data Index: 5514394 (Open Web Text)

Max Activating Token Index: 123

Text #19

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.0177. Min Act: -0.1700

Data Index: 3840840 (Open Web Text)

Max Activating Token Index: 803