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

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

Neuron 3916 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 208857 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0450. Min Act: -0.0002

Data Index: 447251 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0337. Min Act: -0.0002

Data Index: 192209 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0330. Min Act: -0.0002

Data Index: 771234 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0300. Min Act: -0.0002

Data Index: 849461 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0322. Min Act: -0.0002

Data Index: 348847 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1048535 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1828 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1317231 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0300. Min Act: -0.0002

Data Index: 959794 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0285. Min Act: -0.0002

Data Index: 531737 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0286. Min Act: -0.0002

Data Index: 993969 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0281. Min Act: -0.0002

Data Index: 437074 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0296. Min Act: -0.0002

Data Index: 138270 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0280. Min Act: -0.0002

Data Index: 104574 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0262. Min Act: -0.0002

Data Index: 511295 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0294. Min Act: -0.0002

Data Index: 160708 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0254. Min Act: -0.0002

Data Index: 954131 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0261. Min Act: -0.0002

Data Index: 69736 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0247. Min Act: -0.0002

Data Index: 210429 (C4 (Web Text))

Max Activating Token Index: 834