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

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

Neuron 3912 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.9194. Min Act: -0.0000

Data Index: 718857 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.8546. Min Act: -0.0000

Data Index: 529752 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.4498. Min Act: -0.0001

Data Index: 1275088 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.4714. Min Act: -0.0001

Data Index: 943762 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1006632 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.3057. Min Act: -0.0001

Data Index: 163522 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.4309. Min Act: -0.0001

Data Index: 796332 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2905. Min Act: -0.0000

Data Index: 846447 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1141395 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2898. Min Act: -0.0001

Data Index: 576955 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2127. Min Act: -0.0001

Data Index: 399359 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1159985 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2414. Min Act: -0.0001

Data Index: 257327 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2642. Min Act: -0.0000

Data Index: 727011 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2280. Min Act: -0.0000

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2334. Min Act: -0.0001

Data Index: 117976 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.2934. Min Act: -0.0001

Data Index: 75011 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.3587. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.1402. Min Act: -0.0001

Data Index: 249205 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.9194. Min Range: -1.9194

Max Act: 1.1988. Min Act: -0.0000

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 341