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

Dataset: The Pile

Neuron 4374 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.9027. Min Act: -0.0000

Data Index: 717255 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1066231 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1768162 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.3913. Min Act: -0.0000

Data Index: 889627 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.6762. Min Act: -0.0000

Data Index: 792377 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1137485 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1715382 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1309434 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.6161. Min Act: -0.0000

Data Index: 995382 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.3207. Min Act: -0.0000

Data Index: 761156 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.3512. Min Act: -0.0000

Data Index: 968979 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.2373. Min Act: -0.0000

Data Index: 340989 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.0815. Min Act: -0.0000

Data Index: 982537 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.3403. Min Act: -0.0000

Data Index: 771236 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1041129 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1327315 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1635231 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.4640. Min Act: -0.0000

Data Index: 152994 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1175407 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.4390. Min Act: -0.0000

Data Index: 844518 (The Pile)

Max Activating Token Index: 947