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

Dataset: The Pile

Neuron 3481 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4832. Min Act: -0.0000

Data Index: 154588 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3632. Min Act: -0.0000

Data Index: 38062 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1991356 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1912450 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1817455 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1483239 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1883. Min Act: -0.0000

Data Index: 296202 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1511648 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1667456 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2256. Min Act: -0.0000

Data Index: 276357 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1562677 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1055324 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2367. Min Act: -0.0000

Data Index: 364226 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1082829 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1912464 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1278037 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1637023 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1867985 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1781. Min Act: -0.0000

Data Index: 230215 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2116. Min Act: -0.0000

Data Index: 943288 (The Pile)

Max Activating Token Index: 606