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

Dataset: The Pile

Neuron 504 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: 0.3425. Min Range: -0.3425

Max Act: 0.3425. Min Act: -0.0000

Data Index: 39535 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1015368 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2783. Min Act: -0.0000

Data Index: 619391 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2796. Min Act: -0.0000

Data Index: 945697 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1365918 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1140086 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2573. Min Act: -0.0000

Data Index: 364307 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1636145 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2515. Min Act: -0.0000

Data Index: 639974 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1625625 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1974930 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2610. Min Act: -0.0000

Data Index: 952246 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2503. Min Act: -0.0000

Data Index: 540799 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2510. Min Act: -0.0000

Data Index: 38852 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1401798 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2472. Min Act: -0.0000

Data Index: 316420 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1562708 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2639. Min Act: -0.0000

Data Index: 458842 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1107872 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1158742 (The Pile)

Max Activating Token Index: 298