Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 478 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.6503. Min Act: -0.0001

Data Index: 1158418 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3654. Min Act: -0.0001

Data Index: 543580 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3373. Min Act: -0.0001

Data Index: 1293084 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.4880. Min Act: -0.0001

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2949. Min Act: -0.0001

Data Index: 102056 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1794. Min Act: -0.0001

Data Index: 245293 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3189. Min Act: -0.0001

Data Index: 346002 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.3132. Min Act: -0.0001

Data Index: 37032 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1553. Min Act: -0.0001

Data Index: 224373 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2177. Min Act: -0.0001

Data Index: 777799 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1919. Min Act: -0.0001

Data Index: 1003731 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1070448 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2399. Min Act: -0.0001

Data Index: 571578 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1882. Min Act: -0.0001

Data Index: 438056 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.2170. Min Act: -0.0001

Data Index: 808977 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1166. Min Act: -0.0001

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1094. Min Act: -0.0001

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1018. Min Act: -0.0001

Data Index: 700748 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.1051. Min Act: -0.0001

Data Index: 7614 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.6503. Min Range: -1.6503

Max Act: 1.0378. Min Act: -0.0001

Data Index: 1304981 (C4 (Web Text))

Max Activating Token Index: 205