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

Dataset: The Pile

Neuron 1791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.5299. Min Act: -0.0000

Data Index: 1871130 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2871. Min Act: -0.0000

Data Index: 752815 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1059858 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1940669 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2422. Min Act: -0.0000

Data Index: 504821 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2181. Min Act: -0.0000

Data Index: 539063 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2052. Min Act: -0.0000

Data Index: 88271 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1906. Min Act: -0.0000

Data Index: 502511 (The Pile)

Max Activating Token Index: 568

Text #8

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1520357 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1017942 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2070. Min Act: -0.0000

Data Index: 519093 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1311168 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1684. Min Act: -0.0000

Data Index: 899640 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2284. Min Act: -0.0000

Data Index: 835657 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1822. Min Act: -0.0000

Data Index: 619343 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1168036 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1628650 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.1406. Min Act: -0.0000

Data Index: 991212 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1132615 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 1.5299. Min Range: -1.5299

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1577222 (The Pile)

Max Activating Token Index: 123