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

Dataset: Open Web Text

Neuron 1426 in Layer 1

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: 1.7112. Min Range: -1.7112

Max Act: 1.7112. Min Act: -0.1700

Data Index: 7538290 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.7085. Min Act: -0.1688

Data Index: 1194270 (Open Web Text)

Max Activating Token Index: 78

Text #2

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6943. Min Act: -0.1700

Data Index: 869137 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6748. Min Act: -0.1699

Data Index: 6208898 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6629. Min Act: -0.1700

Data Index: 3530538 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6558. Min Act: -0.1700

Data Index: 6234304 (Open Web Text)

Max Activating Token Index: 79

Text #6

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6478. Min Act: -0.1697

Data Index: 798815 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6521. Min Act: -0.1700

Data Index: 1472788 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6375. Min Act: -0.1700

Data Index: 882698 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6348. Min Act: -0.1700

Data Index: 3412134 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6395. Min Act: -0.1699

Data Index: 2856837 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6335. Min Act: -0.1695

Data Index: 2826341 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6352. Min Act: -0.1700

Data Index: 6117168 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6266. Min Act: -0.1700

Data Index: 8706055 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6212. Min Act: -0.1700

Data Index: 1510242 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6169. Min Act: -0.1700

Data Index: 2856838 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6128. Min Act: -0.1700

Data Index: 5015120 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6213. Min Act: -0.1700

Data Index: 2704174 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6169. Min Act: -0.1700

Data Index: 3678858 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6212. Min Act: -0.1700

Data Index: 8300589 (Open Web Text)

Max Activating Token Index: 180