Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4881 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0215. Min Range: -1.0215

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1641812 (Python Code)

Max Activating Token Index: 369

Text #1

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.9610. Min Act: -0.0000

Data Index: 928760 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1620490 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1218165 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1619945 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7027. Min Act: 0.0000

Data Index: 1652668 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7483. Min Act: 0.0001

Data Index: 1603306 (Python Code)

Max Activating Token Index: 406

Text #7

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7315. Min Act: -0.0000

Data Index: 849951 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7369. Min Act: -0.0000

Data Index: 160799 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7345. Min Act: -0.0000

Data Index: 421478 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.7001. Min Act: -0.0000

Data Index: 235892 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1167078 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6794. Min Act: 0.0000

Data Index: 1591982 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6348. Min Act: -0.0000

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1498257 (Python Code)

Max Activating Token Index: 275

Text #15

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6584. Min Act: 0.0001

Data Index: 1431404 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6240. Min Act: -0.0000

Data Index: 543966 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1091740 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.6104. Min Act: -0.0000

Data Index: 324466 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.0215. Min Range: -1.0215

Max Act: 0.5968. Min Act: -0.0000

Data Index: 127735 (C4 (Web Text))

Max Activating Token Index: 395