Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4509 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3719. Min Act: -0.0000

Data Index: 828630 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1120911 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1030719 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2913. Min Act: 0.0001

Data Index: 303422 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2860. Min Act: -0.0000

Data Index: 106370 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2815. Min Act: -0.0000

Data Index: 294876 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2819. Min Act: -0.0000

Data Index: 247429 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2675. Min Act: 0.0000

Data Index: 451957 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2737. Min Act: -0.0000

Data Index: 234817 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2717. Min Act: 0.0000

Data Index: 310759 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2673. Min Act: -0.0000

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2569. Min Act: -0.0000

Data Index: 645801 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2476. Min Act: -0.0000

Data Index: 759810 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1290320 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1251307 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2482. Min Act: -0.0000

Data Index: 273043 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2304. Min Act: 0.0001

Data Index: 203738 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2303. Min Act: -0.0000

Data Index: 587595 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2337. Min Act: -0.0000

Data Index: 888857 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.3719. Min Range: -0.3719

Max Act: 0.2280. Min Act: -0.0000

Data Index: 439576 (C4 (Web Text))

Max Activating Token Index: 875