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

Dataset: The Pile

Neuron 2980 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: 3.1138. Min Range: -3.1138

Max Act: 2.8767. Min Act: -0.0000

Data Index: 547385 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.0979. Min Act: -0.0000

Data Index: 1034062 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6540. Min Act: -0.0000

Data Index: 723186 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7348. Min Act: -0.0000

Data Index: 1129203 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5636. Min Act: -0.0000

Data Index: 285319 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.8205. Min Act: -0.0000

Data Index: 1107554 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.8126. Min Act: -0.0000

Data Index: 1258173 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6829. Min Act: -0.0000

Data Index: 470554 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5603. Min Act: -0.0000

Data Index: 573907 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6988. Min Act: -0.0000

Data Index: 1959527 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.1138. Min Act: -0.0000

Data Index: 645359 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6458. Min Act: -0.0000

Data Index: 1323012 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5442. Min Act: -0.0000

Data Index: 220187 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.0514. Min Act: -0.0000

Data Index: 263575 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5105. Min Act: -0.0000

Data Index: 896528 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5105. Min Act: -0.0000

Data Index: 1974717 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7958. Min Act: -0.0000

Data Index: 812468 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6345. Min Act: -0.0000

Data Index: 1942582 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.9116. Min Act: -0.0000

Data Index: 774199 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7424. Min Act: -0.0000

Data Index: 1708369 (The Pile)

Max Activating Token Index: 886