Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 17 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1116897 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0368. Min Act: -0.0006

Data Index: 892277 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0342. Min Act: -0.0006

Data Index: 447680 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0354. Min Act: -0.0006

Data Index: 75149 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0316. Min Act: -0.0006

Data Index: 415267 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1175243 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0305. Min Act: -0.0006

Data Index: 715649 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0316. Min Act: -0.0006

Data Index: 494854 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1286200 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0304. Min Act: -0.0006

Data Index: 523488 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0297. Min Act: -0.0006

Data Index: 144770 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0308. Min Act: -0.0005

Data Index: 1206668 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0293. Min Act: -0.0006

Data Index: 269450 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1015170 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0280. Min Act: -0.0006

Data Index: 975609 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1359153 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0288. Min Act: -0.0006

Data Index: 122316 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0286. Min Act: -0.0006

Data Index: 460119 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1358396 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0284. Min Act: -0.0006

Data Index: 396076 (C4 (Web Text))

Max Activating Token Index: 665