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

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

Neuron 5449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2254. Min Range: -1.2254

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1162081 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.2254. Min Range: -1.2254

Max Act: 1.0536. Min Act: -0.0000

Data Index: 806993 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.2254. Min Range: -1.2254

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1283368 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9925. Min Act: -0.0000

Data Index: 945048 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1094476 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9454. Min Act: -0.0000

Data Index: 566576 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9316. Min Act: -0.0001

Data Index: 518521 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1026956 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1071931 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9964. Min Act: -0.0001

Data Index: 506959 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8409. Min Act: -0.0000

Data Index: 624563 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9099. Min Act: -0.0001

Data Index: 1340799 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8748. Min Act: -0.0000

Data Index: 596280 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.9023. Min Act: -0.0000

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8697. Min Act: -0.0000

Data Index: 362459 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1342718 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1024963 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1446874 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8874. Min Act: -0.0000

Data Index: 286516 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.2254. Min Range: -1.2254

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1185549 (C4 (Web Text))

Max Activating Token Index: 880