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

Dataset: The Pile

Neuron 4814 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.8278. Min Act: -0.0000

Data Index: 849995 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.7328. Min Act: -0.0000

Data Index: 142881 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6799. Min Act: -0.0000

Data Index: 941521 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6942. Min Act: -0.0000

Data Index: 982095 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6528. Min Act: -0.0000

Data Index: 368631 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1307055 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6518. Min Act: -0.0000

Data Index: 583306 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1747324 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1908209 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1482115 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1557622 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5624. Min Act: -0.0000

Data Index: 873971 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5499. Min Act: -0.0000

Data Index: 606676 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5291. Min Act: -0.0000

Data Index: 28095 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1885161 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1687092 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1507509 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1895307 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5280. Min Act: -0.0000

Data Index: 159131 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1006723 (The Pile)

Max Activating Token Index: 616