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

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

Neuron 3708 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: 1.4906. Min Range: -1.4906

Max Act: 1.4540. Min Act: -0.0000

Data Index: 1195509 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4906. Min Act: -0.0000

Data Index: 552438 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1119554 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2255. Min Act: -0.0000

Data Index: 658767 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1144301 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1106. Min Act: -0.0000

Data Index: 985945 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.0944. Min Act: -0.0000

Data Index: 343853 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1324. Min Act: -0.0000

Data Index: 475297 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1013449 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9532. Min Act: -0.0000

Data Index: 580147 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.0114. Min Act: -0.0000

Data Index: 639120 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9233. Min Act: -0.0000

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9764. Min Act: -0.0000

Data Index: 813067 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1260007 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9292. Min Act: -0.0000

Data Index: 702037 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1098910 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1321877 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.9244. Min Act: -0.0000

Data Index: 928177 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.8164. Min Act: -0.0000

Data Index: 148136 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.4906. Min Range: -1.4906

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1272707 (C4 (Web Text))

Max Activating Token Index: 694