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

Dataset: The Pile

Neuron 2225 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: 0.7104. Min Range: -0.7104

Max Act: 0.7104. Min Act: -0.0000

Data Index: 30707 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1839120 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1640967 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5359. Min Act: 0.0000

Data Index: 1730345 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5177. Min Act: -0.0000

Data Index: 687708 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1627927 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4844. Min Act: -0.0000

Data Index: 454955 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4935. Min Act: -0.0000

Data Index: 155067 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4608. Min Act: 0.0000

Data Index: 1034136 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4659. Min Act: -0.0000

Data Index: 639622 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1271630 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4377. Min Act: -0.0000

Data Index: 206738 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1531212 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1062332 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4200. Min Act: -0.0000

Data Index: 106332 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4389. Min Act: -0.0000

Data Index: 923383 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3788. Min Act: -0.0000

Data Index: 669825 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1189033 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1308827 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3805. Min Act: -0.0000

Data Index: 130985 (The Pile)

Max Activating Token Index: 614