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

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

Neuron 3635 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1164479 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2901. Min Act: 0.0000

Data Index: 377339 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2681. Min Act: 0.0000

Data Index: 166446 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2587. Min Act: 0.0000

Data Index: 376963 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1129371 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2446. Min Act: 0.0000

Data Index: 482546 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1216675 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2349. Min Act: 0.0000

Data Index: 43253 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2236. Min Act: -0.0000

Data Index: 485901 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2300. Min Act: -0.0000

Data Index: 262185 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2240. Min Act: -0.0000

Data Index: 137544 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2217. Min Act: -0.0000

Data Index: 255608 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2098. Min Act: -0.0000

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2231. Min Act: -0.0000

Data Index: 188566 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2129. Min Act: 0.0000

Data Index: 110644 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2050. Min Act: -0.0000

Data Index: 837498 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2082. Min Act: 0.0000

Data Index: 433857 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2070. Min Act: -0.0001

Data Index: 59718 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2031. Min Act: 0.0000

Data Index: 364390 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1946. Min Act: 0.0001

Data Index: 1305608 (C4 (Web Text))

Max Activating Token Index: 35