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

Dataset: The Pile

Neuron 2963 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: 0.5282. Min Range: -0.5282

Max Act: 0.5281. Min Act: -0.0000

Data Index: 950751 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1139279 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4887. Min Act: -0.0000

Data Index: 80057 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4542. Min Act: -0.0000

Data Index: 641289 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4729. Min Act: -0.0000

Data Index: 986785 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3893. Min Act: -0.0000

Data Index: 618801 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4141. Min Act: -0.0000

Data Index: 673055 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1632653 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4050. Min Act: -0.0000

Data Index: 644119 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1440719 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1189940 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1057290 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1251830 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4162. Min Act: -0.0000

Data Index: 469883 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4124. Min Act: -0.0000

Data Index: 85517 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4250. Min Act: -0.0000

Data Index: 643971 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1540071 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4048. Min Act: -0.0000

Data Index: 391576 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1481582 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3909. Min Act: -0.0000

Data Index: 668363 (The Pile)

Max Activating Token Index: 801