Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1935 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.3852. Min Act: -0.0000

Data Index: 133760 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.0790. Min Act: -0.0000

Data Index: 288645 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.1173. Min Act: -0.0000

Data Index: 491962 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1532586 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9160. Min Act: -0.0000

Data Index: 69538 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1399491 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1093507 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9192. Min Act: -0.0000

Data Index: 658110 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9151. Min Act: -0.0000

Data Index: 261028 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8565. Min Act: -0.0000

Data Index: 140010 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1224274 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1334405 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9137. Min Act: -0.0000

Data Index: 872437 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1440282 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8810. Min Act: -0.0000

Data Index: 531985 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8614. Min Act: -0.0000

Data Index: 773577 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1450347 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8719. Min Act: -0.0000

Data Index: 336742 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1628340 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1284878 (C4 (Web Text))

Max Activating Token Index: 660