Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 789 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0006

Data Index: 323139 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0297. Min Act: -0.0006

Data Index: 561249 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0006

Data Index: 10410 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0006

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1177296 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0275. Min Act: -0.0006

Data Index: 405860 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0006

Data Index: 605161 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0006

Data Index: 697587 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0279. Min Act: -0.0006

Data Index: 416836 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0005

Data Index: 875650 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0006

Data Index: 419162 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0269. Min Act: -0.0006

Data Index: 927487 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0271. Min Act: -0.0006

Data Index: 168257 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1145500 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0259. Min Act: -0.0005

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0259. Min Act: -0.0006

Data Index: 422006 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0264. Min Act: -0.0006

Data Index: 229922 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0006

Data Index: 780622 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1190656 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0257. Min Act: -0.0006

Data Index: 516676 (C4 (Web Text))

Max Activating Token Index: 378