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

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

Neuron 5222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3395. Min Range: -2.3395

Max Act: 2.3395. Min Act: -0.0000

Data Index: 513905 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 2.3395. Min Range: -2.3395

Max Act: 2.1746. Min Act: -0.0000

Data Index: 889212 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 2.3395. Min Range: -2.3395

Max Act: 2.1246. Min Act: -0.0000

Data Index: 716427 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 2.3395. Min Range: -2.3395

Max Act: 2.1124. Min Act: -0.0000

Data Index: 151321 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.7867. Min Act: -0.0000

Data Index: 815782 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.7666. Min Act: -0.0000

Data Index: 664036 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6506. Min Act: -0.0000

Data Index: 961545 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6397. Min Act: -0.0000

Data Index: 178515 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1064898 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.7337. Min Act: -0.0000

Data Index: 622876 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.7317. Min Act: -0.0000

Data Index: 977005 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1069657 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6082. Min Act: -0.0000

Data Index: 567748 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6905. Min Act: -0.0000

Data Index: 802115 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.5536. Min Act: -0.0000

Data Index: 897289 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6500. Min Act: -0.0000

Data Index: 440100 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.6338. Min Act: -0.0000

Data Index: 564722 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.5190. Min Act: -0.0000

Data Index: 245461 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.5263. Min Act: -0.0000

Data Index: 682107 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 2.3395. Min Range: -2.3395

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1335322 (C4 (Web Text))

Max Activating Token Index: 97