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

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

Neuron 752 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8257. Min Range: -5.8257

Max Act: 5.8257. Min Act: -0.0000

Data Index: 1031706 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 5.8257. Min Range: -5.8257

Max Act: 4.4237. Min Act: -0.0000

Data Index: 1209018 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 5.8257. Min Range: -5.8257

Max Act: 4.2278. Min Act: -0.0000

Data Index: 1109294 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.6489. Min Act: -0.0000

Data Index: 761710 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.8187. Min Act: -0.0000

Data Index: 945661 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1348676 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.5331. Min Act: -0.0000

Data Index: 1307103 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.6596. Min Act: -0.0000

Data Index: 377170 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.3729. Min Act: -0.0000

Data Index: 303580 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.1006. Min Act: -0.0000

Data Index: 478538 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.0468. Min Act: -0.0000

Data Index: 226818 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 5.8257. Min Range: -5.8257

Max Act: 2.9762. Min Act: -0.0000

Data Index: 409327 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 5.8257. Min Range: -5.8257

Max Act: 2.9155. Min Act: -0.0000

Data Index: 1184574 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.0828. Min Act: -0.0000

Data Index: 90174 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.0879. Min Act: -0.0000

Data Index: 520219 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.1515. Min Act: -0.0000

Data Index: 222882 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.1532. Min Act: -0.0000

Data Index: 784508 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 5.8257. Min Range: -5.8257

Max Act: 2.9860. Min Act: -0.0000

Data Index: 366080 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 5.8257. Min Range: -5.8257

Max Act: 2.8298. Min Act: -0.0000

Data Index: 1115921 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 5.8257. Min Range: -5.8257

Max Act: 3.1210. Min Act: -0.0000

Data Index: 498597 (C4 (Web Text))

Max Activating Token Index: 957