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

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

Neuron 5677 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.7678. Min Act: -0.0000

Data Index: 1424407 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.5636. Min Act: -0.0000

Data Index: 505263 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.5225. Min Act: -0.0000

Data Index: 438323 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.5272. Min Act: -0.0000

Data Index: 610656 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.5016. Min Act: -0.0000

Data Index: 196320 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1171778 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.2986. Min Act: -0.0000

Data Index: 857193 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1045421 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.3823. Min Act: -0.0000

Data Index: 418243 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.3474. Min Act: -0.0000

Data Index: 512533 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1069158 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.1825. Min Act: -0.0000

Data Index: 566684 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.0998. Min Act: -0.0000

Data Index: 778763 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.0825. Min Act: -0.0000

Data Index: 11591 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1241068 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.7678. Min Range: -1.7678

Max Act: 0.9494. Min Act: -0.0000

Data Index: 365862 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.1370. Min Act: -0.0000

Data Index: 492938 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.0600. Min Act: -0.0000

Data Index: 530208 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.1315. Min Act: -0.0000

Data Index: 68632 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.7678. Min Range: -1.7678

Max Act: 1.1274. Min Act: -0.0000

Data Index: 267662 (C4 (Web Text))

Max Activating Token Index: 711