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

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

Neuron 3535 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: 6.1412. Min Range: -6.1412

Max Act: 6.1412. Min Act: -0.0000

Data Index: 737816 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.7193. Min Act: -0.0000

Data Index: 590719 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.8851. Min Act: -0.0000

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.8274. Min Act: -0.0000

Data Index: 1309177 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.5192. Min Act: -0.0000

Data Index: 616961 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 6.1412. Min Range: -6.1412

Max Act: 4.9795. Min Act: -0.0000

Data Index: 1341469 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3301. Min Act: -0.0000

Data Index: 1263633 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3019. Min Act: -0.0000

Data Index: 1035832 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.1158. Min Act: -0.0000

Data Index: 1245568 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.6659. Min Act: -0.0000

Data Index: 735836 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.2916. Min Act: -0.0000

Data Index: 1124697 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.8368. Min Act: -0.0000

Data Index: 425024 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.2409. Min Act: -0.0000

Data Index: 45586 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3931. Min Act: -0.0000

Data Index: 791546 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3893. Min Act: -0.0000

Data Index: 20662 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3571. Min Act: -0.0000

Data Index: 788476 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3167. Min Act: -0.0000

Data Index: 703703 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3086. Min Act: -0.0000

Data Index: 687561 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3091. Min Act: -0.0000

Data Index: 1175789 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 6.1412. Min Range: -6.1412

Max Act: 5.3995. Min Act: -0.0000

Data Index: 266949 (C4 (Web Text))

Max Activating Token Index: 664