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

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

Neuron 2001 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.9240. Min Act: -0.0001

Data Index: 1270289 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.8860. Min Act: -0.0001

Data Index: 298353 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.8029. Min Act: -0.0001

Data Index: 972015 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.8420. Min Act: -0.0001

Data Index: 179617 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7921. Min Act: -0.0001

Data Index: 560103 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.8289. Min Act: -0.0001

Data Index: 236979 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7293. Min Act: -0.0001

Data Index: 466883 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7531. Min Act: -0.0001

Data Index: 887235 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7414. Min Act: -0.0001

Data Index: 448613 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6871. Min Act: -0.0001

Data Index: 176299 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6684. Min Act: -0.0001

Data Index: 228951 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6690. Min Act: -0.0001

Data Index: 564759 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6791. Min Act: -0.0001

Data Index: 995891 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6070. Min Act: -0.0001

Data Index: 68943 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6123. Min Act: -0.0001

Data Index: 110126 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6105. Min Act: -0.0001

Data Index: 535364 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1342942 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6245. Min Act: -0.0001

Data Index: 1265149 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5853. Min Act: -0.0001

Data Index: 1091100 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6131. Min Act: -0.0001

Data Index: 58600 (C4 (Web Text))

Max Activating Token Index: 870