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

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

Neuron 4728 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8750. Min Act: -0.0001

Data Index: 514772 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7244. Min Act: -0.0001

Data Index: 1092344 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5904. Min Act: -0.0001

Data Index: 276090 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1303063 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7427. Min Act: -0.0001

Data Index: 357570 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1224813 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7103. Min Act: -0.0001

Data Index: 1051802 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7117. Min Act: -0.0001

Data Index: 595537 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7104. Min Act: -0.0001

Data Index: 701483 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1304007 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7176. Min Act: -0.0001

Data Index: 923942 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6390. Min Act: -0.0001

Data Index: 295297 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5962. Min Act: -0.0001

Data Index: 988561 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6271. Min Act: -0.0001

Data Index: 990671 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1102432 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5748. Min Act: -0.0001

Data Index: 58850 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6058. Min Act: -0.0001

Data Index: 544816 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6467. Min Act: -0.0001

Data Index: 983786 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6679. Min Act: -0.0001

Data Index: 728733 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6419. Min Act: -0.0001

Data Index: 302575 (C4 (Web Text))

Max Activating Token Index: 190