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

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

Neuron 1368 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: 0.3257. Min Range: -0.3257

Max Act: 0.3173. Min Act: -0.0001

Data Index: 169403 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3257. Min Act: -0.0000

Data Index: 351945 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3022. Min Act: -0.0000

Data Index: 174723 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1332171 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2930. Min Act: -0.0000

Data Index: 894009 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2876. Min Act: -0.0000

Data Index: 252112 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2745. Min Act: -0.0000

Data Index: 416788 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2859. Min Act: -0.0000

Data Index: 10331 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2756. Min Act: -0.0000

Data Index: 133372 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2687. Min Act: -0.0000

Data Index: 721918 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2687. Min Act: -0.0000

Data Index: 899892 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1042398 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2648. Min Act: -0.0000

Data Index: 560520 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2540. Min Act: -0.0000

Data Index: 107576 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1218878 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2395. Min Act: -0.0000

Data Index: 867213 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2545. Min Act: -0.0001

Data Index: 956881 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2546. Min Act: -0.0000

Data Index: 680445 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1009364 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2479. Min Act: -0.0000

Data Index: 332563 (C4 (Web Text))

Max Activating Token Index: 857