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

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

Neuron 4209 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.4328. Min Act: -0.0002

Data Index: 1047818 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3877. Min Act: -0.0002

Data Index: 1090776 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3660. Min Act: -0.0002

Data Index: 435555 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3349. Min Act: -0.0002

Data Index: 1229377 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3505. Min Act: -0.0002

Data Index: 1012440 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3100. Min Act: -0.0002

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2893. Min Act: -0.0002

Data Index: 463774 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2974. Min Act: -0.0002

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2716. Min Act: -0.0002

Data Index: 842285 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2603. Min Act: -0.0002

Data Index: 137444 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2441. Min Act: -0.0002

Data Index: 320499 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2627. Min Act: -0.0002

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2372. Min Act: -0.0002

Data Index: 114713 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2266. Min Act: -0.0002

Data Index: 666622 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1982. Min Act: -0.0002

Data Index: 1232509 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2359. Min Act: -0.0002

Data Index: 832903 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2131. Min Act: -0.0002

Data Index: 1120571 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2055. Min Act: -0.0002

Data Index: 569843 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1970. Min Act: -0.0002

Data Index: 1314972 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2180. Min Act: -0.0002

Data Index: 725707 (C4 (Web Text))

Max Activating Token Index: 901