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

Dataset: The Pile

Neuron 3888 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: 1.3473. Min Range: -1.3473

Max Act: 1.3473. Min Act: -0.0000

Data Index: 185886 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1544722 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1418919 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1114. Min Act: -0.0000

Data Index: 118336 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1324. Min Act: -0.0000

Data Index: 818927 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1193. Min Act: -0.0000

Data Index: 521008 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1733733 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1105955 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1333537 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0777. Min Act: -0.0000

Data Index: 622777 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1180252 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1182000 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0572. Min Act: -0.0000

Data Index: 639880 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9847. Min Act: -0.0000

Data Index: 847295 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0099. Min Act: -0.0000

Data Index: 911452 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1923936 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9989. Min Act: -0.0000

Data Index: 547827 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0005. Min Act: -0.0000

Data Index: 938125 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1297219 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9982. Min Act: -0.0000

Data Index: 555970 (The Pile)

Max Activating Token Index: 504