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

Dataset: The Pile

Neuron 1864 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: 1.4862. Min Range: -1.4862

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1410349 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.4862. Min Act: -0.0000

Data Index: 132550 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1348082 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2254. Min Act: -0.0000

Data Index: 611043 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1493388 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.3102. Min Act: -0.0000

Data Index: 586642 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1865388 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1942091 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2387. Min Act: -0.0000

Data Index: 106349 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1249199 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1822. Min Act: -0.0000

Data Index: 448141 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1780546 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1913044 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2164. Min Act: -0.0000

Data Index: 884061 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1161422 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.2272. Min Act: -0.0000

Data Index: 264434 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.1323. Min Act: -0.0000

Data Index: 762047 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1088204 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.4862. Min Range: -1.4862

Max Act: 1.0559. Min Act: -0.0000

Data Index: 568968 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 1.4862. Min Range: -1.4862

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1121416 (The Pile)

Max Activating Token Index: 995