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

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

Neuron 4153 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: 1.7628. Min Range: -1.7628

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1022228 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.3813. Min Act: -0.0000

Data Index: 1335018 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.2833. Min Act: -0.0000

Data Index: 583883 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.2835. Min Act: -0.0000

Data Index: 333178 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.3983. Min Act: -0.0000

Data Index: 313689 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.2328. Min Act: -0.0000

Data Index: 420383 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.2292. Min Act: -0.0000

Data Index: 145726 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.2077. Min Act: -0.0000

Data Index: 67118 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.1020. Min Act: -0.0000

Data Index: 690643 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.1538. Min Act: -0.0000

Data Index: 423890 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.1093. Min Act: -0.0000

Data Index: 97744 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1175605 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0710. Min Act: -0.0000

Data Index: 964697 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.7628. Min Range: -1.7628

Max Act: 0.8668. Min Act: -0.0000

Data Index: 739564 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1015279 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0356. Min Act: -0.0000

Data Index: 153482 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0224. Min Act: -0.0000

Data Index: 135589 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.0073. Min Act: -0.0000

Data Index: 564569 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.7628. Min Range: -1.7628

Max Act: 0.9468. Min Act: -0.0000

Data Index: 222955 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.1250. Min Act: -0.0000

Data Index: 971061 (C4 (Web Text))

Max Activating Token Index: 732