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

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

Neuron 2550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.5227. Min Act: -0.0001

Data Index: 70432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.4753. Min Act: -0.0001

Data Index: 308681 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.1441. Min Act: -0.0001

Data Index: 487227 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.0475. Min Act: -0.0001

Data Index: 965187 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.7124. Min Act: -0.0001

Data Index: 988159 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.9525. Min Act: -0.0001

Data Index: 1288241 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.9546. Min Act: -0.0001

Data Index: 723195 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.0636. Min Act: -0.0001

Data Index: 998821 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.0478. Min Act: -0.0001

Data Index: 392591 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.1746. Min Act: -0.0001

Data Index: 778367 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.0935. Min Act: -0.0001

Data Index: 221659 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.8690. Min Act: -0.0001

Data Index: 259678 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.8628. Min Act: -0.0001

Data Index: 541984 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.8503. Min Act: -0.0001

Data Index: 846228 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.9387. Min Act: -0.0001

Data Index: 659282 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.9590. Min Act: -0.0001

Data Index: 106653 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.9315. Min Act: -0.0001

Data Index: 127334 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.0326. Min Act: -0.0001

Data Index: 896520 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.4452. Min Act: -0.0001

Data Index: 4463 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 3.5227. Min Range: -3.5227

Max Act: 2.8339. Min Act: -0.0001

Data Index: 1044566 (C4 (Web Text))

Max Activating Token Index: 498