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

Dataset: The Pile

Neuron 4166 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.3278. Min Act: -0.0000

Data Index: 903060 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.1739. Min Act: -0.0000

Data Index: 570869 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1314457 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1916555 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1845327 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9561. Min Act: -0.0000

Data Index: 819440 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9261. Min Act: -0.0000

Data Index: 516340 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1764442 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1775874 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1325321 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1261002 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1865407 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1104479 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8198. Min Act: -0.0000

Data Index: 439822 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1695685 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7428. Min Act: -0.0000

Data Index: 677149 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1733499 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1374484 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7752. Min Act: -0.0000

Data Index: 904747 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8957. Min Act: -0.0000

Data Index: 324749 (The Pile)

Max Activating Token Index: 90