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

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

Neuron 2588 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: 5.1814. Min Range: -5.1814

Max Act: 5.1814. Min Act: -0.0000

Data Index: 531734 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.5405. Min Act: -0.0000

Data Index: 890769 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.4478. Min Act: -0.0000

Data Index: 12252 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.5924. Min Act: -0.0000

Data Index: 624638 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.3975. Min Act: -0.0000

Data Index: 252454 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.5572. Min Act: -0.0000

Data Index: 635791 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.5197. Min Act: -0.0000

Data Index: 610083 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.2643. Min Act: -0.0000

Data Index: 1133207 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.2173. Min Act: -0.0000

Data Index: 675412 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.2165. Min Act: -0.0000

Data Index: 1230026 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.0439. Min Act: -0.0000

Data Index: 225700 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 5.1814. Min Range: -5.1814

Max Act: 4.3768. Min Act: -0.0000

Data Index: 316851 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.9323. Min Act: -0.0000

Data Index: 653546 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.6958. Min Act: -0.0000

Data Index: 145830 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.8627. Min Act: -0.0000

Data Index: 251268 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.8441. Min Act: -0.0000

Data Index: 7258 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.8243. Min Act: -0.0000

Data Index: 357787 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.8236. Min Act: -0.0000

Data Index: 985468 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.7929. Min Act: -0.0000

Data Index: 401094 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 5.1814. Min Range: -5.1814

Max Act: 3.6253. Min Act: -0.0000

Data Index: 777794 (C4 (Web Text))

Max Activating Token Index: 48