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

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

Neuron 4616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0000

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0358. Min Act: -0.0000

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0339. Min Act: -0.0000

Data Index: 243806 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0311. Min Act: -0.0000

Data Index: 404189 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0337. Min Act: -0.0000

Data Index: 25730 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0297. Min Act: -0.0000

Data Index: 388774 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1058392 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1092098 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0275. Min Act: -0.0000

Data Index: 354877 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0289. Min Act: -0.0000

Data Index: 744086 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0300. Min Act: -0.0000

Data Index: 847897 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0272. Min Act: -0.0000

Data Index: 541220 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1130440 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0265. Min Act: -0.0000

Data Index: 986858 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0305. Min Act: -0.0000

Data Index: 535613 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0299. Min Act: -0.0000

Data Index: 454722 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0273. Min Act: -0.0000

Data Index: 1443553 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1342835 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0261. Min Act: -0.0000

Data Index: 170219 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0281. Min Act: -0.0000

Data Index: 900826 (C4 (Web Text))

Max Activating Token Index: 244