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

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

Neuron 1074 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: 3.5200. Min Range: -3.5200

Max Act: 3.5200. Min Act: -0.1700

Data Index: 712503 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.4416. Min Act: -0.1700

Data Index: 1151387 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3946. Min Act: -0.1700

Data Index: 95610 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.4102. Min Act: -0.1700

Data Index: 159520 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3789. Min Act: -0.1700

Data Index: 608268 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3946. Min Act: -0.1700

Data Index: 287717 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3632. Min Act: -0.1700

Data Index: 320845 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3318. Min Act: -0.1700

Data Index: 942558 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3475. Min Act: -0.1700

Data Index: 112491 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3475. Min Act: -0.1700

Data Index: 1060984 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3475. Min Act: -0.1700

Data Index: 129505 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3318. Min Act: -0.1700

Data Index: 1316783 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3318. Min Act: -0.1700

Data Index: 188451 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3161. Min Act: -0.1700

Data Index: 229508 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3318. Min Act: -0.1700

Data Index: 605691 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3161. Min Act: -0.1700

Data Index: 1227838 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3161. Min Act: -0.1700

Data Index: 1123890 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.2847. Min Act: -0.1700

Data Index: 239754 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.3161. Min Act: -0.1700

Data Index: 91064 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 3.5200. Min Range: -3.5200

Max Act: 3.2847. Min Act: -0.1700

Data Index: 928804 (C4 (Web Text))

Max Activating Token Index: 109