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

Dataset: The Pile

Neuron 4680 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: 3.3109. Min Range: -3.3109

Max Act: 3.3109. Min Act: -0.0000

Data Index: 960952 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.0842. Min Act: -0.0000

Data Index: 912288 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.4550. Min Act: -0.0000

Data Index: 845492 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.2940. Min Act: -0.0000

Data Index: 1988189 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1391844 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.2500. Min Act: -0.0000

Data Index: 1231874 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.4070. Min Act: -0.0000

Data Index: 1272199 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.1355. Min Act: -0.0000

Data Index: 1418803 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.2098. Min Act: -0.0000

Data Index: 977076 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1218447 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.0460. Min Act: -0.0000

Data Index: 326186 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 3.3109. Min Range: -3.3109

Max Act: 1.8302. Min Act: -0.0000

Data Index: 121108 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.0335. Min Act: -0.0000

Data Index: 947458 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.0035. Min Act: -0.0000

Data Index: 667481 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 3.3109. Min Range: -3.3109

Max Act: 1.9888. Min Act: -0.0000

Data Index: 508317 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.1027. Min Act: -0.0000

Data Index: 173114 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 3.3109. Min Range: -3.3109

Max Act: 1.9754. Min Act: -0.0000

Data Index: 85153 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.0170. Min Act: -0.0000

Data Index: 453293 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.1669. Min Act: -0.0000

Data Index: 591799 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 3.3109. Min Range: -3.3109

Max Act: 2.2107. Min Act: -0.0000

Data Index: 1519750 (The Pile)

Max Activating Token Index: 635