Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5807 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.7178. Min Act: -0.0000

Data Index: 1091633 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.1370. Min Act: -0.0000

Data Index: 244009 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.1896. Min Act: -0.0000

Data Index: 1023087 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.6688. Min Act: -0.0000

Data Index: 998925 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.0596. Min Act: -0.0000

Data Index: 134792 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.2360. Min Act: -0.0000

Data Index: 185912 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.7163. Min Act: -0.0000

Data Index: 790655 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.1017. Min Act: -0.0000

Data Index: 360209 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.7026. Min Act: -0.0000

Data Index: 705969 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.5103. Min Act: -0.0000

Data Index: 684225 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.5752. Min Act: -0.0000

Data Index: 527145 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 8.7178. Min Range: -8.7178

Max Act: 6.0605. Min Act: -0.0000

Data Index: 575550 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.9849. Min Act: -0.0000

Data Index: 464343 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.0943. Min Act: -0.0000

Data Index: 704777 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.1218. Min Act: -0.0000

Data Index: 419995 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.7972. Min Act: -0.0000

Data Index: 190041 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 8.7178. Min Range: -8.7178

Max Act: 8.1620. Min Act: -0.0000

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.9412. Min Act: -0.0000

Data Index: 1024089 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.7449. Min Act: -0.0000

Data Index: 698882 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 8.7178. Min Range: -8.7178

Max Act: 7.9118. Min Act: -0.0000

Data Index: 366047 (C4 (Web Text))

Max Activating Token Index: 413