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

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

Neuron 5521 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: 0.3091. Min Range: -0.3091

Max Act: 0.3091. Min Act: -0.0000

Data Index: 283549 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2887. Min Act: -0.0000

Data Index: 81480 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1991. Min Act: -0.0000

Data Index: 971490 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2208. Min Act: -0.0000

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1768. Min Act: -0.0000

Data Index: 845912 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1714. Min Act: -0.0000

Data Index: 289254 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1372. Min Act: -0.0000

Data Index: 451943 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1395. Min Act: 0.0000

Data Index: 304724 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1311. Min Act: -0.0000

Data Index: 447844 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1385. Min Act: -0.0000

Data Index: 353375 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1373. Min Act: -0.0000

Data Index: 332589 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1242. Min Act: 0.0000

Data Index: 685495 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1316. Min Act: -0.0000

Data Index: 707098 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1223. Min Act: -0.0000

Data Index: 668759 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1264. Min Act: 0.0001

Data Index: 591320 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1225. Min Act: -0.0000

Data Index: 176759 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1201. Min Act: -0.0000

Data Index: 970448 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1200. Min Act: -0.0000

Data Index: 770367 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1166. Min Act: -0.0000

Data Index: 389636 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1183. Min Act: -0.0000

Data Index: 310969 (C4 (Web Text))

Max Activating Token Index: 38