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

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

Neuron 2823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.5319. Min Act: -0.0000

Data Index: 276747 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.4891. Min Act: -0.0000

Data Index: 244410 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.2620. Min Act: -0.0000

Data Index: 775021 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1855. Min Act: -0.0000

Data Index: 85604 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1543. Min Act: -0.0000

Data Index: 851643 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1451. Min Act: -0.0000

Data Index: 107369 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1048. Min Act: -0.0000

Data Index: 466489 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.0823. Min Act: -0.0000

Data Index: 416783 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.0209. Min Act: -0.0000

Data Index: 305281 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.0044. Min Act: -0.0000

Data Index: 875321 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1214. Min Act: -0.0000

Data Index: 1338142 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 2.5319. Min Range: -2.5319

Max Act: 2.1313. Min Act: -0.0000

Data Index: 38247 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.9392. Min Act: -0.0000

Data Index: 123251 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.9233. Min Act: -0.0000

Data Index: 879787 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.8795. Min Act: -0.0000

Data Index: 185644 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.8842. Min Act: -0.0000

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.9855. Min Act: -0.0000

Data Index: 674164 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.7502. Min Act: -0.0000

Data Index: 582206 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.8546. Min Act: -0.0000

Data Index: 811748 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 2.5319. Min Range: -2.5319

Max Act: 1.7420. Min Act: -0.0000

Data Index: 736725 (C4 (Web Text))

Max Activating Token Index: 257