Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 571 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0003

Data Index: 785244 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0410. Min Act: -0.0003

Data Index: 238965 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0392. Min Act: -0.0004

Data Index: 280628 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0355. Min Act: -0.0003

Data Index: 784961 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0353. Min Act: -0.0003

Data Index: 524230 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0337. Min Act: -0.0003

Data Index: 924514 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1098300 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0303. Min Act: -0.0003

Data Index: 503956 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0335. Min Act: -0.0003

Data Index: 549268 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0317. Min Act: -0.0003

Data Index: 259635 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0322. Min Act: -0.0003

Data Index: 678497 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0311. Min Act: -0.0003

Data Index: 267354 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0317. Min Act: -0.0003

Data Index: 662538 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0313. Min Act: -0.0003

Data Index: 960379 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1391368 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1087051 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1405268 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1654625 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0294. Min Act: -0.0003

Data Index: 108364 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1011002 (C4 (Web Text))

Max Activating Token Index: 438