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

Dataset: The Pile

Neuron 246 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: 1.3302. Min Range: -1.3302

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1195507 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.3302. Min Act: -0.0000

Data Index: 867885 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1619937 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.2022. Min Act: -0.0000

Data Index: 137515 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1144250 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1321002 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1343935 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1577608 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0564. Min Act: -0.0000

Data Index: 803077 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1813667 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1942460 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0531. Min Act: -0.0000

Data Index: 423249 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1208. Min Act: -0.0000

Data Index: 434031 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9624. Min Act: -0.0000

Data Index: 892187 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1756523 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1768155 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1881. Min Act: -0.0000

Data Index: 233080 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0091. Min Act: -0.0000

Data Index: 164067 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0459. Min Act: -0.0000

Data Index: 748682 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0314. Min Act: -0.0000

Data Index: 790503 (The Pile)

Max Activating Token Index: 27