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

Dataset: The Pile

Neuron 4055 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: 1.6053. Min Range: -1.6053

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1478579 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.6053. Min Act: -0.0000

Data Index: 1954524 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4349. Min Act: -0.0000

Data Index: 154310 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4533. Min Act: -0.0000

Data Index: 858755 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4395. Min Act: -0.0000

Data Index: 308659 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4119. Min Act: -0.0000

Data Index: 51428 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1908891 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1901532 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2851. Min Act: -0.0000

Data Index: 600713 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1612748 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1656873 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1212817 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1079721 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2812. Min Act: -0.0000

Data Index: 335715 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1487282 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3434. Min Act: -0.0000

Data Index: 259250 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1512346 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1459073 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2534. Min Act: -0.0000

Data Index: 496146 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2378. Min Act: -0.0000

Data Index: 707678 (The Pile)

Max Activating Token Index: 722