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

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

Neuron 5529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1280423 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0397. Min Act: -0.0002

Data Index: 417769 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0376. Min Act: -0.0002

Data Index: 225665 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1208333 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1316177 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1105822 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1013602 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0345. Min Act: -0.0002

Data Index: 370579 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0345. Min Act: -0.0002

Data Index: 820835 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0343. Min Act: -0.0002

Data Index: 974217 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0336. Min Act: -0.0002

Data Index: 949256 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0339. Min Act: -0.0002

Data Index: 755315 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0332. Min Act: -0.0002

Data Index: 276405 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1102755 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1054470 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1067842 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0315. Min Act: -0.0002

Data Index: 916887 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0289. Min Act: -0.0002

Data Index: 156796 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0315. Min Act: -0.0002

Data Index: 116101 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0309. Min Act: -0.0002

Data Index: 709075 (C4 (Web Text))

Max Activating Token Index: 619