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

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

Neuron 5984 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1105412 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9630. Min Act: -0.0000

Data Index: 342553 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1042422 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1164662 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1297889 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8477. Min Act: -0.0000

Data Index: 374127 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9275. Min Act: -0.0000

Data Index: 478979 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1192893 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1232670 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8632. Min Act: -0.0000

Data Index: 427377 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1046643 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8424. Min Act: -0.0000

Data Index: 679176 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1186011 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1320075 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7479. Min Act: -0.0000

Data Index: 743120 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7926. Min Act: -0.0000

Data Index: 501023 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7598. Min Act: -0.0000

Data Index: 787823 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7710. Min Act: -0.0000

Data Index: 238436 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7571. Min Act: -0.0000

Data Index: 87437 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7707. Min Act: -0.0000

Data Index: 388988 (C4 (Web Text))

Max Activating Token Index: 329