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

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

Neuron 1003 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3159. Min Range: -2.3159

Max Act: 2.3159. Min Act: -0.0000

Data Index: 1154801 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 2.3159. Min Range: -2.3159

Max Act: 2.2572. Min Act: -0.0000

Data Index: 1283862 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.3159. Min Range: -2.3159

Max Act: 2.1227. Min Act: -0.0000

Data Index: 1118104 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8745. Min Act: -0.0000

Data Index: 636930 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8274. Min Act: -0.0000

Data Index: 1560996 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 2.3159. Min Range: -2.3159

Max Act: 2.1064. Min Act: -0.0000

Data Index: 459496 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.9572. Min Act: -0.0000

Data Index: 441387 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1064664 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.9459. Min Act: -0.0000

Data Index: 1078919 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.9159. Min Act: -0.0000

Data Index: 224262 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.7351. Min Act: -0.0000

Data Index: 454399 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8314. Min Act: -0.0000

Data Index: 1199110 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8304. Min Act: -0.0000

Data Index: 690045 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1010839 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8052. Min Act: -0.0000

Data Index: 363622 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8147. Min Act: -0.0000

Data Index: 183999 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.7957. Min Act: -0.0000

Data Index: 526366 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8657. Min Act: -0.0000

Data Index: 40314 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.8877. Min Act: -0.0000

Data Index: 194598 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.7862. Min Act: -0.0000

Data Index: 520979 (C4 (Web Text))

Max Activating Token Index: 95