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

Dataset: Open Web Text

Neuron 1348 in Layer 4

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: 5.1095. Min Range: -5.1095

Max Act: 5.1095. Min Act: -0.1700

Data Index: 6987041 (Open Web Text)

Max Activating Token Index: 857

Text #1

Max Range: 5.1095. Min Range: -5.1095

Max Act: 5.0267. Min Act: -0.1700

Data Index: 8347121 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8807. Min Act: -0.1700

Data Index: 2125919 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8949. Min Act: -0.1700

Data Index: 4604105 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8637. Min Act: -0.1700

Data Index: 1279228 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8309. Min Act: -0.1700

Data Index: 2199410 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8245. Min Act: -0.1700

Data Index: 7857811 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.8071. Min Act: -0.1700

Data Index: 5844857 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7272. Min Act: -0.1700

Data Index: 6129224 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7585. Min Act: -0.1700

Data Index: 1568312 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7178. Min Act: -0.1700

Data Index: 806667 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7552. Min Act: -0.1700

Data Index: 1279221 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7557. Min Act: -0.1700

Data Index: 3886023 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7601. Min Act: -0.1700

Data Index: 1339959 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7639. Min Act: -0.1700

Data Index: 1279229 (Open Web Text)

Max Activating Token Index: 239

Text #15

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7878. Min Act: -0.1700

Data Index: 282203 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7195. Min Act: -0.1700

Data Index: 7141318 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7505. Min Act: -0.1700

Data Index: 3299804 (Open Web Text)

Max Activating Token Index: 377

Text #18

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7153. Min Act: -0.1700

Data Index: 3520479 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 5.1095. Min Range: -5.1095

Max Act: 4.7153. Min Act: -0.1700

Data Index: 3684134 (Open Web Text)

Max Activating Token Index: 459