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

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

Neuron 5724 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: 1.9138. Min Range: -1.9138

Max Act: 1.8265. Min Act: -0.0001

Data Index: 734214 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8430. Min Act: -0.0001

Data Index: 318326 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6320. Min Act: -0.0001

Data Index: 251061 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7023. Min Act: -0.0001

Data Index: 95009 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.9138. Min Act: -0.0001

Data Index: 730610 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5907. Min Act: -0.0001

Data Index: 1069672 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3073. Min Act: -0.0001

Data Index: 724450 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6528. Min Act: -0.0001

Data Index: 333081 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6246. Min Act: -0.0001

Data Index: 719466 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8273. Min Act: -0.0001

Data Index: 1307674 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6398. Min Act: -0.0001

Data Index: 151749 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6227. Min Act: -0.0001

Data Index: 1058419 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5992. Min Act: -0.0001

Data Index: 365721 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6805. Min Act: -0.0001

Data Index: 13866 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6511. Min Act: -0.0001

Data Index: 1308596 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5700. Min Act: -0.0001

Data Index: 1193353 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5369. Min Act: -0.0001

Data Index: 1056406 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4699. Min Act: -0.0001

Data Index: 515256 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1167008 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5637. Min Act: -0.0001

Data Index: 885406 (C4 (Web Text))

Max Activating Token Index: 98