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

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

Neuron 1709 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 121390 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1541. Min Act: -0.0000

Data Index: 575141 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1327. Min Act: -0.0000

Data Index: 172002 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1362. Min Act: -0.0000

Data Index: 419783 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1254. Min Act: -0.0000

Data Index: 294429 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1187. Min Act: -0.0000

Data Index: 611756 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1254. Min Act: -0.0000

Data Index: 358439 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1241. Min Act: -0.0000

Data Index: 751228 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1104. Min Act: -0.0000

Data Index: 864595 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1089. Min Act: -0.0000

Data Index: 329406 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1122. Min Act: -0.0000

Data Index: 159253 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1200. Min Act: -0.0000

Data Index: 760854 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1166. Min Act: -0.0000

Data Index: 522831 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1129. Min Act: -0.0000

Data Index: 936026 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1185. Min Act: -0.0000

Data Index: 519386 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1161. Min Act: -0.0000

Data Index: 429707 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1078. Min Act: -0.0000

Data Index: 547124 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1102. Min Act: -0.0000

Data Index: 893932 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1014. Min Act: -0.0000

Data Index: 806957 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1087. Min Act: -0.0000

Data Index: 290727 (C4 (Web Text))

Max Activating Token Index: 144