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

Dataset: The Pile

Neuron 598 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.4323. Min Act: -0.0000

Data Index: 187651 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1476425 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2864. Min Act: -0.0000

Data Index: 816903 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2315. Min Act: -0.0000

Data Index: 873300 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1871. Min Act: -0.0000

Data Index: 203871 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0952. Min Act: -0.0000

Data Index: 585008 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0024. Min Act: -0.0000

Data Index: 509682 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0963. Min Act: -0.0000

Data Index: 193628 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0552. Min Act: -0.0000

Data Index: 157523 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1286890 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1654060 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9760. Min Act: -0.0000

Data Index: 978125 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9629. Min Act: -0.0000

Data Index: 325864 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9985. Min Act: -0.0000

Data Index: 235913 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1648043 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1059542 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1861275 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9995. Min Act: -0.0000

Data Index: 965714 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1220593 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1484539 (The Pile)

Max Activating Token Index: 11