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

Dataset: Open Web Text

Neuron 1904 in Layer 3

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: 1.8750. Min Range: -1.8750

Max Act: 1.8665. Min Act: -0.1635

Data Index: 3380377 (Open Web Text)

Max Activating Token Index: 102

Text #1

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8584. Min Act: -0.1667

Data Index: 3378751 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8587. Min Act: -0.1688

Data Index: 2864436 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8750. Min Act: -0.1700

Data Index: 418492 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8512. Min Act: -0.1681

Data Index: 1716167 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8439. Min Act: -0.1700

Data Index: 5898300 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8462. Min Act: -0.1700

Data Index: 164818 (Open Web Text)

Max Activating Token Index: 1012

Text #7

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8369. Min Act: -0.1697

Data Index: 50714 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8309. Min Act: -0.1425

Data Index: 5568731 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8326. Min Act: -0.1682

Data Index: 3379127 (Open Web Text)

Max Activating Token Index: 119

Text #10

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8367. Min Act: -0.1691

Data Index: 7373828 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8353. Min Act: -0.1696

Data Index: 6010906 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8365. Min Act: -0.1418

Data Index: 1705999 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8288. Min Act: -0.1395

Data Index: 6151776 (Open Web Text)

Max Activating Token Index: 541

Text #14

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8126. Min Act: -0.1693

Data Index: 4057934 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8148. Min Act: -0.1700

Data Index: 1716168 (Open Web Text)

Max Activating Token Index: 73

Text #16

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8115. Min Act: -0.1665

Data Index: 1606990 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8105. Min Act: -0.1357

Data Index: 3380376 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8029. Min Act: -0.1674

Data Index: 2826835 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.8750. Min Range: -1.8750

Max Act: 1.8142. Min Act: -0.1568

Data Index: 6445889 (Open Web Text)

Max Activating Token Index: 189