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

Dataset: The Pile

Neuron 3644 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: 0.8982. Min Range: -0.8982

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1026863 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.8169. Min Act: -0.0000

Data Index: 566134 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7573. Min Act: -0.0000

Data Index: 53603 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7514. Min Act: -0.0000

Data Index: 417284 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7220. Min Act: -0.0000

Data Index: 40233 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1434050 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6641. Min Act: -0.0000

Data Index: 295305 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6420. Min Act: -0.0000

Data Index: 403973 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1880571 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6807. Min Act: -0.0000

Data Index: 407047 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6169. Min Act: -0.0000

Data Index: 410444 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6374. Min Act: -0.0000

Data Index: 211458 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6367. Min Act: -0.0000

Data Index: 878978 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1880253 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1246776 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5095. Min Act: -0.0000

Data Index: 926413 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1155929 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1968648 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5620. Min Act: -0.0000

Data Index: 972007 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1303001 (The Pile)

Max Activating Token Index: 576