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

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

Neuron 4435 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: 0.8369. Min Range: -0.8369

Max Act: 0.8332. Min Act: -0.0000

Data Index: 112776 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1282525 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7171. Min Act: -0.0000

Data Index: 728585 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7092. Min Act: -0.0000

Data Index: 478557 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1310485 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7150. Min Act: -0.0000

Data Index: 804325 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7221. Min Act: -0.0000

Data Index: 942830 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7007. Min Act: -0.0000

Data Index: 135878 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.7182. Min Act: -0.0000

Data Index: 359457 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.5962. Min Act: -0.0000

Data Index: 551542 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6490. Min Act: -0.0000

Data Index: 667869 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1334529 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1124308 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.5837. Min Act: -0.0000

Data Index: 998690 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1193886 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1227353 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.5899. Min Act: -0.0000

Data Index: 896948 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6257. Min Act: -0.0000

Data Index: 449948 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.8369. Min Range: -0.8369

Max Act: 0.6017. Min Act: -0.0000

Data Index: 35380 (C4 (Web Text))

Max Activating Token Index: 593