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

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

Neuron 1373 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.4173. Min Act: -0.0000

Data Index: 804668 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.3014. Min Act: -0.0000

Data Index: 628064 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.2329. Min Act: -0.0000

Data Index: 26913 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.2204. Min Act: 0.0000

Data Index: 1107414 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.1813. Min Act: -0.0000

Data Index: 89432 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.9444. Min Act: 0.0000

Data Index: 18067 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.2849. Min Act: -0.0000

Data Index: 157987 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.0414. Min Act: -0.0000

Data Index: 1151059 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.0210. Min Act: 0.0000

Data Index: 1267230 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 2.4173. Min Range: -2.4173

Max Act: 2.1280. Min Act: 0.0001

Data Index: 334683 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.9340. Min Act: -0.0000

Data Index: 738891 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.9013. Min Act: -0.0000

Data Index: 320481 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.6800. Min Act: 0.0000

Data Index: 996775 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.7766. Min Act: 0.0000

Data Index: 27220 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.8794. Min Act: -0.0000

Data Index: 443085 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.7462. Min Act: -0.0000

Data Index: 520969 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.6237. Min Act: -0.0000

Data Index: 839069 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.7688. Min Act: 0.0000

Data Index: 1239730 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.8506. Min Act: 0.0000

Data Index: 312000 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.4173. Min Range: -2.4173

Max Act: 1.7526. Min Act: -0.0000

Data Index: 807448 (C4 (Web Text))

Max Activating Token Index: 187