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

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

Neuron 4457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1158036 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1431. Min Act: -0.0002

Data Index: 493011 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1272. Min Act: -0.0002

Data Index: 816624 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1464. Min Act: -0.0002

Data Index: 241279 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1267. Min Act: -0.0002

Data Index: 227659 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1222. Min Act: -0.0002

Data Index: 136891 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1330375 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1161. Min Act: -0.0002

Data Index: 841580 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1167. Min Act: -0.0002

Data Index: 292856 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1099. Min Act: -0.0002

Data Index: 517171 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1052. Min Act: -0.0002

Data Index: 491925 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1128. Min Act: -0.0002

Data Index: 81188 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1109. Min Act: -0.0002

Data Index: 195843 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1149. Min Act: -0.0002

Data Index: 637696 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1106. Min Act: -0.0002

Data Index: 999173 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1011. Min Act: -0.0002

Data Index: 279561 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1041. Min Act: -0.0002

Data Index: 945577 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1062. Min Act: -0.0002

Data Index: 469341 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1027. Min Act: -0.0002

Data Index: 154973 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1096. Min Act: -0.0002

Data Index: 774669 (C4 (Web Text))

Max Activating Token Index: 132