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

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

Neuron 636 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.3270. Min Act: -0.0000

Data Index: 5746 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2673. Min Act: -0.0000

Data Index: 619554 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2529. Min Act: -0.0000

Data Index: 5139 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1228882 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2839. Min Act: -0.0000

Data Index: 884542 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1171901 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2329. Min Act: -0.0000

Data Index: 819156 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2351. Min Act: -0.0000

Data Index: 533461 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2240. Min Act: -0.0000

Data Index: 232599 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2266. Min Act: -0.0000

Data Index: 336702 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1161191 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2419. Min Act: -0.0000

Data Index: 960897 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2327. Min Act: -0.0000

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1628786 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2178. Min Act: -0.0000

Data Index: 239431 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2092. Min Act: -0.0000

Data Index: 747397 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2067. Min Act: -0.0000

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2058. Min Act: -0.0000

Data Index: 550145 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2112. Min Act: -0.0000

Data Index: 249226 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1229608 (C4 (Web Text))

Max Activating Token Index: 663