Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1498834 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0306. Min Act: -0.0002

Data Index: 909194 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1554391 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1383320 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0252. Min Act: -0.0002

Data Index: 511925 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1500962 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1153118 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0248. Min Act: -0.0001

Data Index: 164358 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1602137 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0248. Min Act: -0.0001

Data Index: 57022 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0251. Min Act: -0.0001

Data Index: 247984 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0240. Min Act: -0.0002

Data Index: 762359 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0238. Min Act: -0.0002

Data Index: 756310 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0234. Min Act: -0.0002

Data Index: 211701 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1419701 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0235. Min Act: -0.0002

Data Index: 488787 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0227. Min Act: -0.0002

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1524360 (Python Code)

Max Activating Token Index: 969

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1321543 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1523607 (Python Code)

Max Activating Token Index: 827