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

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

Neuron 191 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.4464. Min Act: -0.0000

Data Index: 315849 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3553. Min Act: -0.0000

Data Index: 480884 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1076321 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3434. Min Act: -0.0000

Data Index: 914010 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3329. Min Act: -0.0000

Data Index: 32196 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1203729 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3180. Min Act: -0.0000

Data Index: 30057 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3275. Min Act: -0.0000

Data Index: 680939 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1209008 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1277254 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1224003 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3107. Min Act: -0.0000

Data Index: 309951 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1076385 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3100. Min Act: -0.0000

Data Index: 826554 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3005. Min Act: -0.0000

Data Index: 607159 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.3055. Min Act: -0.0000

Data Index: 142159 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.2774. Min Act: -0.0000

Data Index: 281987 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.2959. Min Act: -0.0000

Data Index: 451464 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.2947. Min Act: -0.0000

Data Index: 5207 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.4464. Min Range: -0.4464

Max Act: 0.2856. Min Act: -0.0000

Data Index: 382659 (C4 (Web Text))

Max Activating Token Index: 82