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

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

Neuron 758 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0297. Min Range: -2.0297

Max Act: 2.0297. Min Act: -0.0000

Data Index: 227412 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.0297. Min Range: -2.0297

Max Act: 2.0072. Min Act: -0.0000

Data Index: 490271 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.8380. Min Act: -0.0000

Data Index: 177010 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.8270. Min Act: -0.0000

Data Index: 300077 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.9225. Min Act: -0.0000

Data Index: 766095 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.7576. Min Act: -0.0000

Data Index: 657117 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6389. Min Act: -0.0000

Data Index: 650067 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.7702. Min Act: -0.0000

Data Index: 397757 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6565. Min Act: -0.0000

Data Index: 311643 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6394. Min Act: -0.0000

Data Index: 534239 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6468. Min Act: -0.0000

Data Index: 21179 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6505. Min Act: -0.0000

Data Index: 1030920 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.6243. Min Act: -0.0000

Data Index: 40195 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.5722. Min Act: -0.0000

Data Index: 58864 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.5598. Min Act: -0.0000

Data Index: 774603 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.5482. Min Act: -0.0000

Data Index: 525144 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1218506 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1111429 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1035359 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 2.0297. Min Range: -2.0297

Max Act: 1.5837. Min Act: -0.0000

Data Index: 1271756 (C4 (Web Text))

Max Activating Token Index: 223