Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 744 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1072319 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8615. Min Act: -0.0000

Data Index: 886492 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.7249. Min Act: -0.0000

Data Index: 1275417 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2427. Min Act: -0.0000

Data Index: 721494 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0508. Min Act: -0.0000

Data Index: 650687 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3718. Min Act: -0.0000

Data Index: 95642 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1138857 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3200. Min Act: -0.0000

Data Index: 822053 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2347. Min Act: -0.0000

Data Index: 21603 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1114356 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2477. Min Act: -0.0000

Data Index: 207306 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0328. Min Act: -0.0000

Data Index: 130087 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.1823. Min Act: -0.0000

Data Index: 354835 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0335. Min Act: -0.0000

Data Index: 798708 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2852. Min Act: -0.0000

Data Index: 681174 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0218. Min Act: -0.0000

Data Index: 921189 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.9241. Min Range: -1.9241

Max Act: 0.9762. Min Act: -0.0000

Data Index: 136350 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0242. Min Act: -0.0000

Data Index: 920144 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1108772 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.0491. Min Act: -0.0000

Data Index: 86659 (C4 (Web Text))

Max Activating Token Index: 667