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

Dataset: The Pile

Neuron 4042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.9268. Min Act: -0.0000

Data Index: 1182146 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.1806. Min Act: -0.0000

Data Index: 1151178 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.3199. Min Act: -0.0000

Data Index: 1770897 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.6324. Min Act: -0.0000

Data Index: 23025 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.1880. Min Act: -0.0000

Data Index: 272859 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.2028. Min Act: -0.0000

Data Index: 1458386 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.1877. Min Act: -0.0000

Data Index: 62569 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.2965. Min Act: -0.0000

Data Index: 99873 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.2428. Min Act: -0.0000

Data Index: 1023092 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.3298. Min Act: -0.0000

Data Index: 1074843 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.3433. Min Act: -0.0000

Data Index: 602479 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.1612. Min Act: -0.0000

Data Index: 317576 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.0819. Min Act: -0.0000

Data Index: 1272952 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.0647. Min Act: -0.0000

Data Index: 974348 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.0363. Min Act: -0.0000

Data Index: 1326334 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.3063. Min Act: -0.0000

Data Index: 822605 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 3.9268. Min Range: -3.9268

Max Act: 2.9102. Min Act: -0.0000

Data Index: 1329370 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 3.9268. Min Range: -3.9268

Max Act: 2.9850. Min Act: -0.0000

Data Index: 842117 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 3.9268. Min Range: -3.9268

Max Act: 2.7252. Min Act: -0.0000

Data Index: 1502150 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 3.9268. Min Range: -3.9268

Max Act: 2.9807. Min Act: -0.0000

Data Index: 1849020 (The Pile)

Max Activating Token Index: 228