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

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

Neuron 3234 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: 1.6198. Min Range: -1.6198

Max Act: 1.6198. Min Act: -0.0000

Data Index: 1557359 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1590382 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1536614 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3382. Min Act: -0.0000

Data Index: 693403 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1538635 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1085504 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1372579 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1400558 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1501. Min Act: -0.0000

Data Index: 642283 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2118. Min Act: -0.0000

Data Index: 534864 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1566826 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1616. Min Act: -0.0000

Data Index: 401723 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1595. Min Act: -0.0000

Data Index: 944986 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1587896 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1559237 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1364. Min Act: -0.0000

Data Index: 141855 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1466169 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1220. Min Act: -0.0000

Data Index: 43603 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1243. Min Act: -0.0000

Data Index: 23358 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1372362 (Python Code)

Max Activating Token Index: 678