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

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

Neuron 5346 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: 1.2413. Min Range: -1.2413

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1165490 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.2413. Min Range: -1.2413

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1345050 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1316319 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8582. Min Act: -0.0000

Data Index: 271717 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8866. Min Act: -0.0000

Data Index: 69019 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8304. Min Act: -0.0000

Data Index: 864891 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1116885 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8509. Min Act: -0.0000

Data Index: 684659 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1324203 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8321. Min Act: -0.0000

Data Index: 419587 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1184311 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8176. Min Act: -0.0000

Data Index: 844773 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8166. Min Act: -0.0000

Data Index: 13433 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8641. Min Act: -0.0000

Data Index: 650720 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1201770 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7890. Min Act: -0.0000

Data Index: 984641 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1079428 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7825. Min Act: -0.0000

Data Index: 474222 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7264. Min Act: -0.0000

Data Index: 263107 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7430. Min Act: -0.0000

Data Index: 798896 (C4 (Web Text))

Max Activating Token Index: 467