Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3006 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7292. Min Act: -0.0002

Data Index: 174884 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1266267 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6439. Min Act: -0.0001

Data Index: 524599 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6296. Min Act: -0.0002

Data Index: 646360 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6258. Min Act: -0.0002

Data Index: 281706 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5853. Min Act: -0.0002

Data Index: 227693 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5672. Min Act: -0.0001

Data Index: 836430 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5130. Min Act: -0.0002

Data Index: 522524 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5458. Min Act: -0.0001

Data Index: 462401 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5588. Min Act: -0.0002

Data Index: 745041 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5435. Min Act: -0.0001

Data Index: 494100 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4980. Min Act: -0.0001

Data Index: 1032340 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5137. Min Act: -0.0002

Data Index: 733980 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5685. Min Act: -0.0002

Data Index: 706818 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5220. Min Act: -0.0002

Data Index: 767965 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5005. Min Act: -0.0002

Data Index: 363931 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4161. Min Act: -0.0002

Data Index: 1327073 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4608. Min Act: -0.0002

Data Index: 175476 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4924. Min Act: -0.0002

Data Index: 155211 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4617. Min Act: -0.0002

Data Index: 981800 (C4 (Web Text))

Max Activating Token Index: 543