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

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

Neuron 3346 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.5675. Min Range: -13.5675

Max Act: 13.5001. Min Act: -0.0002

Data Index: 859790 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 13.5675. Min Range: -13.5675

Max Act: 13.5675. Min Act: -0.0001

Data Index: 16428 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 13.5675. Min Range: -13.5675

Max Act: 13.5055. Min Act: -0.0002

Data Index: 1006289 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 13.5675. Min Range: -13.5675

Max Act: 13.2256. Min Act: -0.0002

Data Index: 45447 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.8672. Min Act: -0.0002

Data Index: 349068 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.5036. Min Act: -0.0002

Data Index: 762535 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.3433. Min Act: -0.0002

Data Index: 716858 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.2014. Min Act: -0.0002

Data Index: 772074 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.2309. Min Act: -0.0002

Data Index: 621775 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 13.5675. Min Range: -13.5675

Max Act: 12.0350. Min Act: -0.0002

Data Index: 293536 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 13.5675. Min Range: -13.5675

Max Act: 11.9046. Min Act: -0.0002

Data Index: 369710 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 13.5675. Min Range: -13.5675

Max Act: 11.8264. Min Act: -0.0002

Data Index: 813235 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 13.5675. Min Range: -13.5675

Max Act: 11.7366. Min Act: -0.0002

Data Index: 1153307 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 13.5675. Min Range: -13.5675

Max Act: 11.3354. Min Act: -0.0002

Data Index: 1056243 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 13.5675. Min Range: -13.5675

Max Act: 11.0477. Min Act: -0.0002

Data Index: 244352 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 13.5675. Min Range: -13.5675

Max Act: 10.9943. Min Act: -0.0002

Data Index: 83298 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 13.5675. Min Range: -13.5675

Max Act: 10.8869. Min Act: -0.0002

Data Index: 161490 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 13.5675. Min Range: -13.5675

Max Act: 10.6256. Min Act: -0.0002

Data Index: 602886 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 13.5675. Min Range: -13.5675

Max Act: 0.0184. Min Act: -0.0002

Data Index: 620317 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 13.5675. Min Range: -13.5675

Max Act: 0.0172. Min Act: -0.0002

Data Index: 331101 (C4 (Web Text))

Max Activating Token Index: 656