Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4217 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.7844. Min Act: -0.0002

Data Index: 314229 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6687. Min Act: -0.0002

Data Index: 115873 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6432. Min Act: -0.0002

Data Index: 1003526 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6247. Min Act: -0.0002

Data Index: 393174 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5932. Min Act: -0.0002

Data Index: 101911 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5911. Min Act: -0.0002

Data Index: 928490 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4908. Min Act: -0.0002

Data Index: 958657 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5477. Min Act: -0.0002

Data Index: 1305796 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5001. Min Act: -0.0002

Data Index: 953359 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4360. Min Act: -0.0002

Data Index: 768100 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4845. Min Act: -0.0002

Data Index: 1352194 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4685. Min Act: -0.0002

Data Index: 431277 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4090. Min Act: -0.0002

Data Index: 1034573 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4004. Min Act: -0.0002

Data Index: 1185190 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4707. Min Act: -0.0002

Data Index: 969350 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4152. Min Act: -0.0003

Data Index: 576460 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3757. Min Act: -0.0003

Data Index: 931812 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4245. Min Act: -0.0002

Data Index: 74098 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3953. Min Act: -0.0002

Data Index: 730665 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3748. Min Act: -0.0002

Data Index: 939862 (C4 (Web Text))

Max Activating Token Index: 129