Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4731 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1010308 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1285453 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1167202 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3570. Min Act: -0.0000

Data Index: 175844 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1269604 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3216. Min Act: -0.0000

Data Index: 640507 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3307. Min Act: -0.0000

Data Index: 276527 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3085. Min Act: -0.0000

Data Index: 146858 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3255. Min Act: -0.0000

Data Index: 597883 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3185. Min Act: -0.0000

Data Index: 554838 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3056. Min Act: -0.0000

Data Index: 935992 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1145054 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1153742 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3017. Min Act: -0.0000

Data Index: 903705 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3111. Min Act: -0.0000

Data Index: 210014 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3008. Min Act: -0.0000

Data Index: 305549 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3216. Min Act: -0.0000

Data Index: 13985 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3011. Min Act: -0.0000

Data Index: 452160 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3010. Min Act: -0.0000

Data Index: 716822 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3183. Min Act: -0.0000

Data Index: 459272 (C4 (Web Text))

Max Activating Token Index: 244