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

Dataset: The Pile

Neuron 886 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: 1.6007. Min Range: -1.6007

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1516558 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1194826 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.3565. Min Act: -0.0000

Data Index: 515738 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1844542 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1907195 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1466304 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1485591 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2180. Min Act: -0.0000

Data Index: 834093 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1886835 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1964. Min Act: -0.0000

Data Index: 785560 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1150966 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1301236 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1396652 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1663549 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1904367 (The Pile)

Max Activating Token Index: 85

Text #15

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1197959 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1962407 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0685. Min Act: -0.0000

Data Index: 204194 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.0909. Min Act: -0.0000

Data Index: 646381 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 1.6007. Min Range: -1.6007

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1050974 (The Pile)

Max Activating Token Index: 137