Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.4898. Min Act: -0.0000

Data Index: 619800 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1311088 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3574. Min Act: -0.0000

Data Index: 973650 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3289. Min Act: -0.0000

Data Index: 558523 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3226. Min Act: -0.0000

Data Index: 870456 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3190. Min Act: -0.0001

Data Index: 615170 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3295. Min Act: -0.0000

Data Index: 429884 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2997. Min Act: -0.0000

Data Index: 213278 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3060. Min Act: -0.0000

Data Index: 838528 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2924. Min Act: -0.0001

Data Index: 68726 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.3112. Min Act: -0.0000

Data Index: 84325 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1282112 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2808. Min Act: -0.0001

Data Index: 525800 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2858. Min Act: -0.0000

Data Index: 132086 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1049381 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2766. Min Act: -0.0000

Data Index: 882498 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2824. Min Act: -0.0000

Data Index: 805674 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1315659 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1356924 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.4898. Min Range: -0.4898

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1257625 (C4 (Web Text))

Max Activating Token Index: 763