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

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

Neuron 2041 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.8241. Min Act: -0.0000

Data Index: 333780 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1276155 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6998. Min Act: -0.0000

Data Index: 538197 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1208529 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6436. Min Act: -0.0000

Data Index: 328918 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1433953 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1061411 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6274. Min Act: -0.0000

Data Index: 38945 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1003793 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1041803 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6013. Min Act: -0.0000

Data Index: 514969 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6144. Min Act: -0.0000

Data Index: 32661 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6098. Min Act: -0.0000

Data Index: 113542 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.5906. Min Act: -0.0000

Data Index: 486515 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.5921. Min Act: -0.0000

Data Index: 719194 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.5705. Min Act: -0.0000

Data Index: 234003 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.6285. Min Act: -0.0000

Data Index: 286248 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.5894. Min Act: -0.0000

Data Index: 218334 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.8241. Min Range: -0.8241

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1642066 (Python Code)

Max Activating Token Index: 402