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

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

Neuron 3360 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: 0.8269. Min Range: -0.8269

Max Act: 0.8269. Min Act: -0.0002

Data Index: 969610 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7359. Min Act: -0.0002

Data Index: 56203 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7205. Min Act: -0.0002

Data Index: 1084711 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7084. Min Act: -0.0002

Data Index: 1099643 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6826. Min Act: -0.0002

Data Index: 683968 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6712. Min Act: -0.0002

Data Index: 832111 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6538. Min Act: -0.0002

Data Index: 912544 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6472. Min Act: -0.0002

Data Index: 794383 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6427. Min Act: -0.0002

Data Index: 239930 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6293. Min Act: -0.0002

Data Index: 517541 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6462. Min Act: -0.0002

Data Index: 446384 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6305. Min Act: -0.0002

Data Index: 821067 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6189. Min Act: -0.0002

Data Index: 1244216 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6356. Min Act: -0.0002

Data Index: 952911 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6319. Min Act: -0.0002

Data Index: 1239702 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6183. Min Act: -0.0002

Data Index: 217074 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6149. Min Act: -0.0002

Data Index: 1132233 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6286. Min Act: -0.0002

Data Index: 1258015 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6065. Min Act: -0.0002

Data Index: 176332 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6115. Min Act: -0.0002

Data Index: 173476 (C4 (Web Text))

Max Activating Token Index: 265