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

Dataset: Open Web Text

Neuron 1378 in Layer 2

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: 2.0547. Min Range: -2.0547

Max Act: 2.0471. Min Act: -0.1700

Data Index: 976229 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 2.0547. Min Range: -2.0547

Max Act: 2.0547. Min Act: -0.1107

Data Index: 6736572 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9775. Min Act: -0.1700

Data Index: 3228364 (Open Web Text)

Max Activating Token Index: 314

Text #3

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9957. Min Act: -0.1700

Data Index: 961739 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9707. Min Act: -0.1699

Data Index: 5104415 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9411. Min Act: -0.1700

Data Index: 3228366 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9654. Min Act: -0.1700

Data Index: 7569649 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9463. Min Act: -0.1700

Data Index: 3228362 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9399. Min Act: -0.1697

Data Index: 3287409 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9602. Min Act: -0.0916

Data Index: 6736579 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9423. Min Act: -0.1699

Data Index: 8118131 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9182. Min Act: -0.1700

Data Index: 8625266 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9149. Min Act: -0.1700

Data Index: 1153949 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9251. Min Act: -0.1700

Data Index: 3228360 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9292. Min Act: -0.1697

Data Index: 3228367 (Open Web Text)

Max Activating Token Index: 141

Text #15

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9191. Min Act: -0.1700

Data Index: 2472723 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9425. Min Act: -0.0825

Data Index: 4475098 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9032. Min Act: -0.1592

Data Index: 2522174 (Open Web Text)

Max Activating Token Index: 725

Text #18

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9166. Min Act: -0.1700

Data Index: 3287410 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.9191. Min Act: -0.1700

Data Index: 3228363 (Open Web Text)

Max Activating Token Index: 51