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

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

Neuron 3698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1245215 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1402810 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.0394. Min Act: -0.0000

Data Index: 479198 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9781. Min Act: -0.0000

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9540. Min Act: -0.0000

Data Index: 473641 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8454. Min Act: -0.0000

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1349321 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9244. Min Act: -0.0000

Data Index: 949984 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9064. Min Act: -0.0000

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1379101 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9759. Min Act: -0.0000

Data Index: 282201 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8760. Min Act: -0.0000

Data Index: 268699 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8806. Min Act: -0.0000

Data Index: 2430 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9169. Min Act: -0.0000

Data Index: 26119 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9813. Min Act: -0.0000

Data Index: 210105 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1188939 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1634274 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1380736 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8754. Min Act: -0.0000

Data Index: 69357 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8404. Min Act: -0.0000

Data Index: 298449 (C4 (Web Text))

Max Activating Token Index: 950