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

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

Neuron 341 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7205. Min Range: -2.7205

Max Act: 2.7205. Min Act: -0.0000

Data Index: 165788 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.9042. Min Act: -0.0000

Data Index: 41563 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.4429. Min Act: -0.0000

Data Index: 422296 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.5459. Min Act: -0.0000

Data Index: 496690 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.4023. Min Act: -0.0000

Data Index: 437897 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.3118. Min Act: -0.0000

Data Index: 777667 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.3240. Min Act: 0.0000

Data Index: 1024183 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.2336. Min Act: -0.0000

Data Index: 615014 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1043267 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.7205. Min Range: -2.7205

Max Act: 0.9942. Min Act: -0.0000

Data Index: 731092 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0850. Min Act: -0.0000

Data Index: 580385 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0597. Min Act: -0.0000

Data Index: 43438 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0571. Min Act: -0.0000

Data Index: 696663 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0974. Min Act: -0.0000

Data Index: 33462 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0048. Min Act: -0.0000

Data Index: 58197 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 2.7205. Min Range: -2.7205

Max Act: 0.9631. Min Act: -0.0000

Data Index: 81422 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 2.7205. Min Range: -2.7205

Max Act: 1.0199. Min Act: -0.0000

Data Index: 126902 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 2.7205. Min Range: -2.7205

Max Act: 0.9764. Min Act: -0.0000

Data Index: 6443 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 2.7205. Min Range: -2.7205

Max Act: 0.9358. Min Act: -0.0000

Data Index: 570735 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 2.7205. Min Range: -2.7205

Max Act: 0.8842. Min Act: -0.0000

Data Index: 993895 (C4 (Web Text))

Max Activating Token Index: 344