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

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

Neuron 1037 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.4239. Min Act: -0.0000

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.3421. Min Act: -0.0000

Data Index: 158196 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.3296. Min Act: -0.0000

Data Index: 421637 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.3183. Min Act: -0.0000

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1526656 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1633326 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.3105. Min Act: -0.0000

Data Index: 538852 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1564895 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1217272 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2392. Min Act: -0.0000

Data Index: 226025 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1022209 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2258. Min Act: -0.0000

Data Index: 600516 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2153. Min Act: -0.0000

Data Index: 183397 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1648727 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2238. Min Act: -0.0000

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1378498 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1373713 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2082. Min Act: -0.0000

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.5246. Min Range: -0.5246

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1526147 (Python Code)

Max Activating Token Index: 636