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

Dataset: The Pile

Neuron 3347 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: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1505983 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1595997 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1050. Min Act: -0.0000

Data Index: 64324 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9929. Min Act: -0.0000

Data Index: 466378 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0741. Min Act: -0.0000

Data Index: 74892 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1649. Min Act: -0.0000

Data Index: 101092 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1481734 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9240. Min Act: -0.0000

Data Index: 333591 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1574504 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1845878 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9699. Min Act: -0.0000

Data Index: 712319 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0059. Min Act: -0.0000

Data Index: 662881 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1316749 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1868978 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1991274 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1813535 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1384276 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9173. Min Act: -0.0000

Data Index: 919015 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8945. Min Act: 0.0000

Data Index: 94762 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1848598 (The Pile)

Max Activating Token Index: 305