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

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

Neuron 5606 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: 1.1919. Min Range: -1.1919

Max Act: 1.1919. Min Act: -0.0000

Data Index: 428925 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9635. Min Act: -0.0000

Data Index: 951702 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0892. Min Act: -0.0000

Data Index: 613696 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0590. Min Act: -0.0000

Data Index: 903443 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1037345 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1240047 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1063325 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9665. Min Act: -0.0000

Data Index: 825147 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1181365 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1064775 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9069. Min Act: -0.0000

Data Index: 920156 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9488. Min Act: -0.0000

Data Index: 707360 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1047019 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.7510. Min Act: -0.0000

Data Index: 676228 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8598. Min Act: -0.0000

Data Index: 158736 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1015172 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8707. Min Act: -0.0000

Data Index: 64996 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1056999 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.7981. Min Act: -0.0000

Data Index: 951850 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8037. Min Act: -0.0000

Data Index: 732771 (C4 (Web Text))

Max Activating Token Index: 136