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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1181 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.4082. Min Act: -0.0000

Data Index: 665232 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3948. Min Act: -0.0000

Data Index: 989636 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3998. Min Act: -0.0000

Data Index: 363120 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3769. Min Act: -0.0000

Data Index: 816951 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1010323 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1318798 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1264839 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3408. Min Act: -0.0000

Data Index: 167483 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3417. Min Act: -0.0000

Data Index: 722364 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1030186 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3233. Min Act: -0.0000

Data Index: 806200 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3019. Min Act: -0.0000

Data Index: 101951 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1018759 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1081265 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3090. Min Act: -0.0000

Data Index: 326803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3079. Min Act: -0.0000

Data Index: 728652 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3031. Min Act: -0.0000

Data Index: 43553 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1123488 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1041063 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3098. Min Act: -0.0000

Data Index: 823891 (C4 (Web Text))

Max Activating Token Index: 886