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

Dataset: The Pile

Neuron 1498 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: 0.4374. Min Range: -0.4374

Max Act: 0.4374. Min Act: 0.0000

Data Index: 1997063 (The Pile)

Max Activating Token Index: 741

Text #1

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3271. Min Act: -0.0000

Data Index: 907290 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3628. Min Act: -0.0000

Data Index: 480898 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3605. Min Act: -0.0000

Data Index: 998880 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3406. Min Act: 0.0000

Data Index: 294231 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3268. Min Act: -0.0000

Data Index: 627892 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3065. Min Act: -0.0000

Data Index: 604549 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3040. Min Act: -0.0000

Data Index: 97808 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1460683 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3247. Min Act: -0.0000

Data Index: 512412 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2831. Min Act: -0.0000

Data Index: 151780 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1171817 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3216. Min Act: -0.0000

Data Index: 904551 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1634790 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2795. Min Act: -0.0000

Data Index: 284613 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1075971 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1032261 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1730260 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2409. Min Act: -0.0000

Data Index: 511485 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2834. Min Act: -0.0000

Data Index: 574401 (The Pile)

Max Activating Token Index: 858