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

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

Neuron 5036 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: 0.9446. Min Range: -0.9446

Max Act: 0.9446. Min Act: 0.0000

Data Index: 317183 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8046. Min Act: 0.0000

Data Index: 811453 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8479. Min Act: -0.0000

Data Index: 146321 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8113. Min Act: 0.0001

Data Index: 144766 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1211483 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7301. Min Act: -0.0000

Data Index: 436725 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7396. Min Act: -0.0000

Data Index: 696980 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1208230 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6912. Min Act: -0.0000

Data Index: 946256 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1334274 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7027. Min Act: -0.0000

Data Index: 107143 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6296. Min Act: -0.0000

Data Index: 801678 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6407. Min Act: 0.0000

Data Index: 348746 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6140. Min Act: -0.0000

Data Index: 655335 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6540. Min Act: -0.0000

Data Index: 615068 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6284. Min Act: 0.0000

Data Index: 685416 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1064007 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6236. Min Act: -0.0000

Data Index: 91746 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1138764 (C4 (Web Text))

Max Activating Token Index: 544