Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 15 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.3971. Min Act: -0.0000

Data Index: 348556 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.3036. Min Act: -0.0000

Data Index: 1077792 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.4295. Min Act: -0.0000

Data Index: 329986 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.2076. Min Act: -0.0000

Data Index: 826030 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.2372. Min Act: -0.0000

Data Index: 606407 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.3309. Min Act: -0.0000

Data Index: 1107335 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.9435. Min Act: -0.0000

Data Index: 772324 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 2.4295. Min Range: -2.4295

Max Act: 2.0326. Min Act: -0.0000

Data Index: 355444 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.7402. Min Act: -0.0000

Data Index: 1097383 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.7004. Min Act: -0.0000

Data Index: 197121 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.7954. Min Act: -0.0000

Data Index: 489664 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6429. Min Act: -0.0000

Data Index: 130218 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6853. Min Act: -0.0000

Data Index: 462409 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6616. Min Act: -0.0000

Data Index: 49073 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1253041 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6569. Min Act: -0.0000

Data Index: 875590 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6262. Min Act: -0.0000

Data Index: 145321 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6407. Min Act: -0.0000

Data Index: 627046 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6323. Min Act: -0.0000

Data Index: 279627 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 2.4295. Min Range: -2.4295

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1204539 (C4 (Web Text))

Max Activating Token Index: 546