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

Dataset: The Pile

Neuron 2700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.8272. Min Act: -0.0000

Data Index: 1512464 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1168412 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1213712 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9868. Min Act: -0.0000

Data Index: 241866 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1822843 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9573. Min Act: -0.0000

Data Index: 888163 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9798. Min Act: -0.0000

Data Index: 794378 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.8867. Min Act: -0.0000

Data Index: 548369 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1008878 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1311825 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1014477 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1167885 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9529. Min Act: -0.0000

Data Index: 932163 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1426773 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9404. Min Act: -0.0000

Data Index: 931638 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1029165 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1263293 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.0486. Min Act: -0.0000

Data Index: 328248 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9214. Min Act: -0.0000

Data Index: 836152 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 1.8272. Min Range: -1.8272

Max Act: 0.9222. Min Act: -0.0000

Data Index: 248475 (The Pile)

Max Activating Token Index: 1001