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

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

Neuron 1842 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.7910. Min Act: -0.0000

Data Index: 1324714 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 6.3067. Min Range: -6.3067

Max Act: 6.3067. Min Act: -0.0001

Data Index: 130220 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.3277. Min Act: -0.0000

Data Index: 966648 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.8308. Min Act: -0.0001

Data Index: 1223708 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.8919. Min Act: -0.0000

Data Index: 981447 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.5448. Min Act: -0.0001

Data Index: 490432 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.9699. Min Act: -0.0001

Data Index: 571416 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.2725. Min Act: -0.0000

Data Index: 241728 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.2951. Min Act: -0.0001

Data Index: 1311489 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.3397. Min Act: -0.0001

Data Index: 570993 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.9729. Min Act: -0.0000

Data Index: 1094168 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.7922. Min Act: -0.0000

Data Index: 696578 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.1210. Min Act: -0.0001

Data Index: 376253 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.0763. Min Act: -0.0001

Data Index: 1207015 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.7154. Min Act: -0.0000

Data Index: 146526 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.8348. Min Act: -0.0000

Data Index: 1092598 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.8116. Min Act: -0.0000

Data Index: 1125729 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.9732. Min Act: -0.0001

Data Index: 749326 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 6.3067. Min Range: -6.3067

Max Act: 4.7275. Min Act: -0.0000

Data Index: 565003 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 6.3067. Min Range: -6.3067

Max Act: 5.3064. Min Act: -0.0000

Data Index: 1316242 (C4 (Web Text))

Max Activating Token Index: 942