Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 761 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.7890. Min Act: -0.1700

Data Index: 1357060 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.6325. Min Act: -0.1700

Data Index: 848559 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.6638. Min Act: -0.1700

Data Index: 179453 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1197047 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5699. Min Act: -0.1700

Data Index: 762843 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5385. Min Act: -0.1700

Data Index: 1339818 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1056027 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5385. Min Act: -0.1700

Data Index: 589108 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5385. Min Act: -0.1700

Data Index: 219775 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.4915. Min Act: -0.1700

Data Index: 981842 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5229. Min Act: -0.1700

Data Index: 452803 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5229. Min Act: -0.1700

Data Index: 891690 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5072. Min Act: -0.1700

Data Index: 1260192 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5072. Min Act: -0.1700

Data Index: 558935 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5229. Min Act: -0.1700

Data Index: 526653 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5072. Min Act: -0.1700

Data Index: 293602 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.4915. Min Act: -0.1700

Data Index: 647535 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5072. Min Act: -0.1700

Data Index: 1081432 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.4602. Min Act: -0.1700

Data Index: 643662 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 3.7890. Min Range: -3.7890

Max Act: 3.5072. Min Act: -0.1700

Data Index: 794148 (C4 (Web Text))

Max Activating Token Index: 1017