Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2666 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.3219. Min Act: -0.0000

Data Index: 9457 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.3402. Min Act: -0.0000

Data Index: 519592 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1647150 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1625526 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2554. Min Act: -0.0000

Data Index: 970828 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2117. Min Act: -0.0000

Data Index: 485042 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1106771 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1553529 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1791. Min Act: -0.0000

Data Index: 26898 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2365. Min Act: -0.0000

Data Index: 980882 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1954354 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1605. Min Act: -0.0000

Data Index: 733340 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1864. Min Act: -0.0000

Data Index: 293151 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1586888 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1925158 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2285. Min Act: -0.0000

Data Index: 425592 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1759327 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1705. Min Act: -0.0000

Data Index: 685464 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1213. Min Act: -0.0000

Data Index: 940532 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1947000 (The Pile)

Max Activating Token Index: 821