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

Dataset: The Pile

Neuron 2747 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: 1.2425. Min Range: -1.2425

Max Act: 1.2381. Min Act: -0.0000

Data Index: 798038 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1381454 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0782. Min Act: -0.0000

Data Index: 717519 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.1292. Min Act: -0.0000

Data Index: 880888 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.1332. Min Act: -0.0000

Data Index: 768861 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1449970 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1213233 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9834. Min Act: -0.0000

Data Index: 683315 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1250514 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1775264 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1663790 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0101. Min Act: -0.0000

Data Index: 468780 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1589254 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0039. Min Act: -0.0000

Data Index: 854761 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9742. Min Act: -0.0000

Data Index: 501013 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1000704 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9946. Min Act: -0.0000

Data Index: 103008 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9471. Min Act: -0.0000

Data Index: 618700 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1855517 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1201309 (The Pile)

Max Activating Token Index: 290