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

Dataset: The Pile

Neuron 1199 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1344670 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1407358 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1527828 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1059. Min Act: -0.0000

Data Index: 343490 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1765357 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0909. Min Act: -0.0000

Data Index: 848926 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1804721 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9786. Min Act: -0.0000

Data Index: 471644 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9824. Min Act: -0.0000

Data Index: 959714 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9762. Min Act: -0.0000

Data Index: 940515 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1544630 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1312762 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1669309 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1669317 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1544041 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8303. Min Act: -0.0000

Data Index: 239254 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8753. Min Act: -0.0000

Data Index: 367406 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8424. Min Act: -0.0000

Data Index: 168643 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1811470 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1621892 (The Pile)

Max Activating Token Index: 581