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

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

Neuron 3978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5344. Min Act: -0.0000

Data Index: 69979 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4636. Min Act: -0.0001

Data Index: 208823 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4653. Min Act: -0.0000

Data Index: 36177 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4344. Min Act: -0.0001

Data Index: 729338 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1284676 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3907. Min Act: -0.0000

Data Index: 902256 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3768. Min Act: -0.0000

Data Index: 820462 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3997. Min Act: -0.0000

Data Index: 836853 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4085. Min Act: -0.0000

Data Index: 218590 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1229602 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1178119 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3845. Min Act: -0.0000

Data Index: 140671 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3762. Min Act: -0.0001

Data Index: 537525 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3457. Min Act: -0.0000

Data Index: 773679 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1151940 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3452. Min Act: -0.0000

Data Index: 194436 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3657. Min Act: -0.0000

Data Index: 112942 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1348199 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1054892 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3542. Min Act: -0.0000

Data Index: 29308 (C4 (Web Text))

Max Activating Token Index: 1022