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

Dataset: The Pile

Neuron 808 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: 0.5355. Min Range: -0.5355

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1268592 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.5122. Min Act: -0.0000

Data Index: 583813 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4794. Min Act: -0.0000

Data Index: 862674 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4578. Min Act: -0.0000

Data Index: 708646 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4338. Min Act: -0.0000

Data Index: 381919 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4208. Min Act: -0.0000

Data Index: 400718 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1907147 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4430. Min Act: -0.0000

Data Index: 291352 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1443551 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1466231 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1310652 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1810170 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3762. Min Act: -0.0000

Data Index: 734784 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4196. Min Act: -0.0000

Data Index: 972895 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4164. Min Act: -0.0000

Data Index: 389335 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3985. Min Act: -0.0000

Data Index: 746501 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1399237 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1471415 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4216. Min Act: -0.0000

Data Index: 549344 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4084. Min Act: -0.0000

Data Index: 356867 (The Pile)

Max Activating Token Index: 662