Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1159 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6315. Min Act: -0.1700

Data Index: 533821 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6471. Min Act: -0.1700

Data Index: 182905 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1199019 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6315. Min Act: -0.1700

Data Index: 735929 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6158. Min Act: -0.1700

Data Index: 553003 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1104238 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5845. Min Act: -0.1700

Data Index: 869074 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5688. Min Act: -0.1700

Data Index: 243247 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5845. Min Act: -0.1700

Data Index: 229781 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5845. Min Act: -0.1700

Data Index: 114339 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5688. Min Act: -0.1700

Data Index: 676326 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 443860 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5375. Min Act: -0.1700

Data Index: 507292 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5218. Min Act: -0.1700

Data Index: 1063661 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5375. Min Act: -0.1700

Data Index: 574609 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 965659 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5532. Min Act: -0.1700

Data Index: 787472 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1177406 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1101040 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5532. Min Act: -0.1700

Data Index: 798543 (C4 (Web Text))

Max Activating Token Index: 587