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

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

Neuron 3679 in Layer 0

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: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0001

Data Index: 785233 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0200. Min Act: -0.0001

Data Index: 279049 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0201. Min Act: -0.0001

Data Index: 373397 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0197. Min Act: -0.0001

Data Index: 124634 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0197. Min Act: -0.0001

Data Index: 509923 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0198. Min Act: -0.0001

Data Index: 44588 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0195. Min Act: -0.0001

Data Index: 503488 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1246146 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0194. Min Act: -0.0001

Data Index: 770841 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0195. Min Act: -0.0001

Data Index: 99863 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0195. Min Act: -0.0001

Data Index: 23028 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0001

Data Index: 715405 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1200995 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0001

Data Index: 949830 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1345741 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1272533 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0001

Data Index: 902872 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0001

Data Index: 679914 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1101497 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0001

Data Index: 611720 (C4 (Web Text))

Max Activating Token Index: 131