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

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

Neuron 2470 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: 1.8493. Min Range: -1.8493

Max Act: 1.8493. Min Act: -0.0003

Data Index: 231927 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.8051. Min Act: -0.0002

Data Index: 723752 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.7050. Min Act: -0.0003

Data Index: 686731 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.6358. Min Act: -0.0002

Data Index: 357246 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.6593. Min Act: -0.0002

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.6282. Min Act: -0.0002

Data Index: 136046 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.6367. Min Act: -0.0002

Data Index: 667768 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.6253. Min Act: -0.0002

Data Index: 1034281 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5947. Min Act: -0.0002

Data Index: 1031174 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5539. Min Act: -0.0002

Data Index: 1139483 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5751. Min Act: -0.0002

Data Index: 1026653 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5725. Min Act: -0.0002

Data Index: 1072547 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5614. Min Act: -0.0002

Data Index: 164653 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5703. Min Act: -0.0002

Data Index: 970660 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5245. Min Act: -0.0002

Data Index: 451571 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5763. Min Act: -0.0002

Data Index: 787618 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5689. Min Act: -0.0002

Data Index: 389355 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5477. Min Act: -0.0002

Data Index: 819288 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5397. Min Act: -0.0002

Data Index: 572763 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5334. Min Act: -0.0002

Data Index: 355753 (C4 (Web Text))

Max Activating Token Index: 25