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

Dataset: The Pile

Neuron 2634 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: 3.1138. Min Range: -3.1138

Max Act: 3.1138. Min Act: -0.0000

Data Index: 1620678 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5306. Min Act: -0.0000

Data Index: 453632 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3835. Min Act: -0.0000

Data Index: 1633980 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.4849. Min Act: -0.0000

Data Index: 1752413 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2909. Min Act: -0.0000

Data Index: 499674 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3613. Min Act: -0.0000

Data Index: 1839813 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2328. Min Act: -0.0000

Data Index: 575969 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2222. Min Act: -0.0000

Data Index: 495477 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2107. Min Act: -0.0000

Data Index: 2205 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.1114. Min Act: -0.0000

Data Index: 1018023 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2352. Min Act: -0.0000

Data Index: 1729627 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2108. Min Act: -0.0000

Data Index: 1840866 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.0826. Min Act: -0.0000

Data Index: 954583 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.1897. Min Act: -0.0000

Data Index: 1211406 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.1965. Min Act: -0.0000

Data Index: 1634021 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.3166. Min Act: -0.0000

Data Index: 823658 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.0655. Min Act: -0.0000

Data Index: 884130 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.1634. Min Act: -0.0000

Data Index: 362189 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.2840. Min Act: -0.0000

Data Index: 586597 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1186324 (The Pile)

Max Activating Token Index: 997