Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1650 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1481901 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1649409 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1428317 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0235. Min Act: -0.0003

Data Index: 293035 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1614593 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1601532 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1446813 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1498348 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1411055 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1603660 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0181. Min Act: -0.0003

Data Index: 444801 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1594282 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1443738 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1636137 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0169. Min Act: -0.0003

Data Index: 331536 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1586691 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0165. Min Act: -0.0003

Data Index: 194810 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0163. Min Act: -0.0004

Data Index: 373444 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0166. Min Act: -0.0003

Data Index: 26353 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0161. Min Act: -0.0003

Data Index: 505220 (C4 (Web Text))

Max Activating Token Index: 278