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

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

Neuron 4104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9949. Min Act: -0.0000

Data Index: 231314 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1208888 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9270. Min Act: -0.0000

Data Index: 730471 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1195158 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9846. Min Act: -0.0000

Data Index: 677574 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.8217. Min Act: -0.0000

Data Index: 654572 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7438. Min Act: -0.0000

Data Index: 894935 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7642. Min Act: -0.0000

Data Index: 452512 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7782. Min Act: -0.0000

Data Index: 342374 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.6782. Min Act: -0.0000

Data Index: 810546 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1236241 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1168686 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.8062. Min Act: -0.0000

Data Index: 889038 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7939. Min Act: -0.0000

Data Index: 867128 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1241444 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7498. Min Act: -0.0000

Data Index: 223880 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7019. Min Act: -0.0000

Data Index: 946428 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1097178 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.6922. Min Act: -0.0000

Data Index: 978437 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.7229. Min Act: -0.0000

Data Index: 761841 (C4 (Web Text))

Max Activating Token Index: 128