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

Dataset: The Pile

Neuron 2722 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1403. Min Act: 0.0000

Data Index: 955651 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1106. Min Act: -0.0000

Data Index: 807589 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1175424 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1543. Min Act: -0.0000

Data Index: 993575 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0536. Min Act: -0.0000

Data Index: 560796 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9830. Min Act: -0.0000

Data Index: 35796 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1212195 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1166889 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9461. Min Act: -0.0000

Data Index: 80633 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1950036 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1482396 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1258153 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9406. Min Act: -0.0000

Data Index: 523268 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1008014 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0002. Min Act: 0.0000

Data Index: 245473 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9562. Min Act: 0.0000

Data Index: 1432865 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1928001 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1406332 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1297576 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1911249 (The Pile)

Max Activating Token Index: 223