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

Dataset: The Pile

Neuron 4192 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: 0.2848. Min Range: -0.2848

Max Act: 0.2848. Min Act: -0.0000

Data Index: 406269 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1658391 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1017808 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2362. Min Act: -0.0000

Data Index: 591714 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1552191 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1154940 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1218286 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1186407 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2307. Min Act: -0.0000

Data Index: 378084 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1860713 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1742059 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1155146 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1905741 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1732870 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2009. Min Act: -0.0000

Data Index: 419361 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1063636 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1988117 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2046. Min Act: -0.0000

Data Index: 406906 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2042. Min Act: -0.0000

Data Index: 560429 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1888. Min Act: -0.0000

Data Index: 105978 (The Pile)

Max Activating Token Index: 856