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

Dataset: The Pile

Neuron 91 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7082. Min Act: -0.0000

Data Index: 832857 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1647187 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1381197 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1879047 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1450697 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5970. Min Act: -0.0000

Data Index: 22616 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5714. Min Act: -0.0000

Data Index: 559423 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6548. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5534. Min Act: -0.0000

Data Index: 624219 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5486. Min Act: -0.0000

Data Index: 663741 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5720. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1150296 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5078. Min Act: -0.0000

Data Index: 90274 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4965. Min Act: -0.0000

Data Index: 602129 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5157. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1975065 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1116647 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5187. Min Act: -0.0000

Data Index: 982071 (The Pile)

Max Activating Token Index: 955