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

Dataset: The Pile

Neuron 2127 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: 0.5953. Min Range: -0.5953

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1151967 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.5114. Min Act: -0.0000

Data Index: 215991 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1305799 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.5583. Min Act: -0.0000

Data Index: 52010 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4028. Min Act: -0.0000

Data Index: 613901 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4482. Min Act: -0.0000

Data Index: 995864 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4598. Min Act: -0.0000

Data Index: 14052 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1797713 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1360172 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4061. Min Act: -0.0000

Data Index: 153919 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1039585 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3840. Min Act: -0.0000

Data Index: 48294 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3777. Min Act: -0.0000

Data Index: 229251 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1643271 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1329728 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1562075 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1435447 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1710831 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1090796 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.5953. Min Range: -0.5953

Max Act: 0.3820. Min Act: -0.0000

Data Index: 545341 (The Pile)

Max Activating Token Index: 723