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

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

Neuron 1409 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5303. Min Range: -5.5303

Max Act: 5.5303. Min Act: -0.0000

Data Index: 176813 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 5.5303. Min Range: -5.5303

Max Act: 5.2416. Min Act: -0.0000

Data Index: 548479 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 5.5303. Min Range: -5.5303

Max Act: 5.3468. Min Act: -0.0000

Data Index: 354681 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 5.5303. Min Range: -5.5303

Max Act: 5.3083. Min Act: -0.0000

Data Index: 431113 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 5.5303. Min Range: -5.5303

Max Act: 5.2239. Min Act: -0.0000

Data Index: 42077 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.9217. Min Act: -0.0000

Data Index: 920366 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.9987. Min Act: -0.0000

Data Index: 1149207 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.8493. Min Act: -0.0000

Data Index: 945172 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.8411. Min Act: -0.0000

Data Index: 1121389 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6337. Min Act: -0.0000

Data Index: 816812 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6268. Min Act: -0.0000

Data Index: 180818 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6494. Min Act: -0.0000

Data Index: 1098401 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6377. Min Act: -0.0000

Data Index: 399804 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6862. Min Act: -0.0000

Data Index: 335247 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.5120. Min Act: -0.0000

Data Index: 21091 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.8439. Min Act: -0.0000

Data Index: 15793 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6355. Min Act: -0.0000

Data Index: 140587 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.8037. Min Act: -0.0000

Data Index: 1112071 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.6272. Min Act: -0.0000

Data Index: 1225253 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 5.5303. Min Range: -5.5303

Max Act: 4.7877. Min Act: -0.0000

Data Index: 956475 (C4 (Web Text))

Max Activating Token Index: 754