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

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

Neuron 3089 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 995430 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0318. Min Act: -0.0002

Data Index: 967466 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0318. Min Act: -0.0002

Data Index: 994300 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0305. Min Act: -0.0002

Data Index: 305073 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0275. Min Act: -0.0002

Data Index: 404762 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0275. Min Act: -0.0002

Data Index: 416605 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0258. Min Act: -0.0002

Data Index: 696398 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1153948 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0264. Min Act: -0.0002

Data Index: 196377 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0250. Min Act: -0.0002

Data Index: 753970 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0258. Min Act: -0.0002

Data Index: 147135 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0236. Min Act: -0.0002

Data Index: 580290 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0232. Min Act: -0.0002

Data Index: 10201 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0236. Min Act: -0.0002

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1183926 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0242. Min Act: -0.0002

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0223. Min Act: -0.0003

Data Index: 377640 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0236. Min Act: -0.0002

Data Index: 596183 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0219. Min Act: -0.0002

Data Index: 176092 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0222. Min Act: -0.0002

Data Index: 744265 (C4 (Web Text))

Max Activating Token Index: 822