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

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

Neuron 1535 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1138779 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4554. Min Act: -0.0000

Data Index: 551231 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1136422 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4432. Min Act: -0.0000

Data Index: 174661 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4410. Min Act: -0.0000

Data Index: 446949 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4362. Min Act: -0.0000

Data Index: 421532 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3868. Min Act: -0.0000

Data Index: 206705 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3840. Min Act: -0.0000

Data Index: 431308 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3818. Min Act: -0.0000

Data Index: 499953 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3660. Min Act: -0.0000

Data Index: 651636 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3620. Min Act: -0.0000

Data Index: 772451 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3572. Min Act: -0.0000

Data Index: 89834 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3325. Min Act: -0.0000

Data Index: 405902 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3254. Min Act: -0.0000

Data Index: 731699 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3219. Min Act: -0.0000

Data Index: 762444 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3259. Min Act: -0.0000

Data Index: 29180 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3021. Min Act: -0.0000

Data Index: 798745 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2968. Min Act: -0.0000

Data Index: 198704 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3013. Min Act: -0.0000

Data Index: 309761 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3011. Min Act: 0.0000

Data Index: 1164140 (C4 (Web Text))

Max Activating Token Index: 30