Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.4052. Min Act: -0.0001

Data Index: 66415 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1193545 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3800. Min Act: -0.0000

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3609. Min Act: -0.0000

Data Index: 441507 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3607. Min Act: -0.0000

Data Index: 997370 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3386. Min Act: -0.0001

Data Index: 445417 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3757. Min Act: -0.0001

Data Index: 294630 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3511. Min Act: -0.0001

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3468. Min Act: -0.0000

Data Index: 916440 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3821. Min Act: -0.0000

Data Index: 933384 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3608. Min Act: -0.0000

Data Index: 832958 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1080283 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1087746 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3171. Min Act: -0.0000

Data Index: 443912 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1095247 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3305. Min Act: -0.0000

Data Index: 876305 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3271. Min Act: -0.0001

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1070848 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3259. Min Act: -0.0001

Data Index: 406022 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3373. Min Act: -0.0001

Data Index: 555093 (C4 (Web Text))

Max Activating Token Index: 82