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

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

Neuron 21 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.6192. Min Act: -0.0001

Data Index: 528368 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1051272 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4451. Min Act: -0.0001

Data Index: 618185 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4231. Min Act: -0.0000

Data Index: 206720 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1249830 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1351164 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3918. Min Act: -0.0001

Data Index: 34642 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4127. Min Act: -0.0000

Data Index: 61384 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4017. Min Act: 0.0000

Data Index: 118942 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1328308 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3538. Min Act: -0.0000

Data Index: 51686 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1202629 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3627. Min Act: -0.0001

Data Index: 384451 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1265182 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3420. Min Act: -0.0001

Data Index: 890536 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3318. Min Act: -0.0001

Data Index: 307878 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3444. Min Act: 0.0000

Data Index: 490008 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3278. Min Act: -0.0001

Data Index: 35345 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1294782 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3037. Min Act: -0.0001

Data Index: 209425 (C4 (Web Text))

Max Activating Token Index: 372