Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2761 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.7272. Min Act: -0.0001

Data Index: 14515 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.5496. Min Act: -0.0000

Data Index: 203560 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.5037. Min Act: -0.0001

Data Index: 1549221 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4655. Min Act: -0.0001

Data Index: 12234 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4165. Min Act: -0.0001

Data Index: 782037 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1431456 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.3279. Min Act: -0.0001

Data Index: 1214701 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.3150. Min Act: -0.0001

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2629. Min Act: -0.0001

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2993. Min Act: -0.0001

Data Index: 233649 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2828. Min Act: -0.0001

Data Index: 1182854 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1243678 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2416. Min Act: -0.0001

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2256. Min Act: -0.0000

Data Index: 206782 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2286. Min Act: -0.0000

Data Index: 15896 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2239. Min Act: -0.0001

Data Index: 990673 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1298129 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2712. Min Act: -0.0001

Data Index: 1239193 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2580. Min Act: -0.0001

Data Index: 594553 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.2045. Min Act: -0.0001

Data Index: 117008 (C4 (Web Text))

Max Activating Token Index: 312