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

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

Neuron 1653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1309034 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9149. Min Act: -0.0000

Data Index: 512991 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7461. Min Act: -0.0000

Data Index: 839575 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7332. Min Act: -0.0000

Data Index: 45046 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1176516 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6966. Min Act: -0.0000

Data Index: 901598 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6764. Min Act: -0.0000

Data Index: 876606 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7160. Min Act: -0.0000

Data Index: 73568 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6852. Min Act: -0.0000

Data Index: 312452 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6616. Min Act: -0.0000

Data Index: 580347 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6773. Min Act: -0.0000

Data Index: 204573 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6273. Min Act: -0.0000

Data Index: 97348 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6241. Min Act: -0.0000

Data Index: 524041 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1242735 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1221698 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1288980 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6093. Min Act: -0.0001

Data Index: 931994 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1080360 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6026. Min Act: -0.0000

Data Index: 92108 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6225. Min Act: -0.0000

Data Index: 964318 (C4 (Web Text))

Max Activating Token Index: 278