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

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

Neuron 4879 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: 1.6726. Min Range: -1.6726

Max Act: 1.6726. Min Act: -0.0001

Data Index: 1276992 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1127737 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.3241. Min Act: -0.0001

Data Index: 1290953 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1066. Min Act: -0.0001

Data Index: 1002929 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.2634. Min Act: -0.0001

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.2566. Min Act: -0.0001

Data Index: 240974 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.3208. Min Act: -0.0001

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1839. Min Act: -0.0001

Data Index: 635440 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.2546. Min Act: -0.0000

Data Index: 743635 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1755. Min Act: -0.0001

Data Index: 938100 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.2274. Min Act: -0.0001

Data Index: 405349 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1181. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.1347. Min Act: -0.0001

Data Index: 136431 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0935. Min Act: -0.0001

Data Index: 434319 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0829. Min Act: -0.0001

Data Index: 78282 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.6726. Min Range: -1.6726

Max Act: 0.9858. Min Act: -0.0001

Data Index: 252426 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0351. Min Act: -0.0001

Data Index: 1025197 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0900. Min Act: -0.0001

Data Index: 620754 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1099838 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.6726. Min Range: -1.6726

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1620470 (Python Code)

Max Activating Token Index: 340