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

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

Neuron 1973 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.8927. Min Act: -0.0001

Data Index: 1001149 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.6430. Min Act: -0.0001

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.3525. Min Act: -0.0001

Data Index: 693428 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.1380. Min Act: -0.0001

Data Index: 992267 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.1782. Min Act: -0.0001

Data Index: 898565 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.4596. Min Act: -0.0001

Data Index: 897037 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.0186. Min Act: -0.0001

Data Index: 1265700 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.9564. Min Act: -0.0001

Data Index: 344244 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.1064. Min Act: -0.0001

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.2330. Min Act: -0.0001

Data Index: 739046 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.0784. Min Act: -0.0001

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.0831. Min Act: -0.0001

Data Index: 490186 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 3.8927. Min Range: -3.8927

Max Act: 3.0488. Min Act: -0.0001

Data Index: 1075277 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.9757. Min Act: -0.0001

Data Index: 445893 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.8820. Min Act: -0.0001

Data Index: 1054304 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.8203. Min Act: -0.0001

Data Index: 635176 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.6853. Min Act: -0.0001

Data Index: 677106 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.9065. Min Act: -0.0001

Data Index: 757322 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.6032. Min Act: -0.0001

Data Index: 561014 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.8927. Min Range: -3.8927

Max Act: 2.7279. Min Act: -0.0001

Data Index: 1092628 (C4 (Web Text))

Max Activating Token Index: 246