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

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

Neuron 468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.3351. Min Act: -0.0000

Data Index: 954481 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.1040. Min Act: -0.0000

Data Index: 422899 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.5149. Min Act: -0.0000

Data Index: 417442 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7898. Min Act: -0.0000

Data Index: 668579 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.5330. Min Act: -0.0000

Data Index: 473417 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1103838 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4898. Min Act: -0.0000

Data Index: 927598 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.5577. Min Act: -0.0000

Data Index: 552343 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4618. Min Act: -0.0000

Data Index: 189404 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4963. Min Act: -0.0000

Data Index: 280894 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4469. Min Act: -0.0000

Data Index: 240127 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1208188 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4354. Min Act: -0.0000

Data Index: 483503 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4421. Min Act: -0.0000

Data Index: 948571 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4229. Min Act: -0.0000

Data Index: 712153 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.2074. Min Act: -0.0000

Data Index: 589911 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4308. Min Act: -0.0000

Data Index: 949013 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.3633. Min Act: -0.0000

Data Index: 370590 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.4130. Min Act: -0.0000

Data Index: 64137 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.1176. Min Act: -0.0000

Data Index: 986174 (C4 (Web Text))

Max Activating Token Index: 644