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

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

Neuron 2584 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0004

Data Index: 212542 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0291. Min Act: -0.0004

Data Index: 278360 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0269. Min Act: -0.0004

Data Index: 1004043 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0317. Min Act: -0.0004

Data Index: 593828 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0266. Min Act: -0.0004

Data Index: 47831 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0262. Min Act: -0.0004

Data Index: 911585 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0273. Min Act: -0.0004

Data Index: 536287 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0261. Min Act: -0.0004

Data Index: 858398 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0246. Min Act: -0.0004

Data Index: 1470593 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0236. Min Act: -0.0004

Data Index: 1284657 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0198. Min Act: -0.0004

Data Index: 175348 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0253. Min Act: -0.0004

Data Index: 543579 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0257. Min Act: -0.0004

Data Index: 42583 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0247. Min Act: -0.0004

Data Index: 193968 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0236. Min Act: -0.0004

Data Index: 115132 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0295. Min Act: -0.0004

Data Index: 19323 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0239. Min Act: -0.0004

Data Index: 747175 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0209. Min Act: -0.0004

Data Index: 521165 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0252. Min Act: -0.0004

Data Index: 772858 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0236. Min Act: -0.0004

Data Index: 331346 (C4 (Web Text))

Max Activating Token Index: 566