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

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

Neuron 3444 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1213229 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0002

Data Index: 989185 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0320. Min Act: -0.0002

Data Index: 100965 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0318. Min Act: -0.0003

Data Index: 41227 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0314. Min Act: -0.0003

Data Index: 734588 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0311. Min Act: -0.0003

Data Index: 922256 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0311. Min Act: -0.0003

Data Index: 416594 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0308. Min Act: -0.0003

Data Index: 470187 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0307. Min Act: -0.0002

Data Index: 241188 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0307. Min Act: -0.0003

Data Index: 105501 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1313648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0306. Min Act: -0.0003

Data Index: 294549 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0306. Min Act: -0.0003

Data Index: 54575 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0306. Min Act: -0.0003

Data Index: 574521 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1294728 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0305. Min Act: -0.0002

Data Index: 799977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0305. Min Act: -0.0002

Data Index: 258780 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0304. Min Act: -0.0003

Data Index: 653893 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0297. Min Act: -0.0003

Data Index: 166595 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0302. Min Act: -0.0002

Data Index: 256359 (C4 (Web Text))

Max Activating Token Index: 188