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

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

Neuron 3860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8051. Min Act: -0.0000

Data Index: 607640 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7801. Min Act: -0.0000

Data Index: 641220 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8270. Min Act: -0.0000

Data Index: 39116 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7859. Min Act: -0.0000

Data Index: 848647 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7515. Min Act: -0.0000

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7430. Min Act: -0.0000

Data Index: 642329 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7236. Min Act: -0.0001

Data Index: 445499 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7207. Min Act: -0.0001

Data Index: 654369 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1264265 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1479829 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7201. Min Act: -0.0000

Data Index: 102160 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7064. Min Act: -0.0000

Data Index: 359794 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6886. Min Act: -0.0000

Data Index: 260692 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6264. Min Act: -0.0001

Data Index: 328775 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6207. Min Act: -0.0000

Data Index: 816172 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6791. Min Act: -0.0000

Data Index: 227263 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6265. Min Act: -0.0000

Data Index: 284811 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1309220 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6265. Min Act: -0.0000

Data Index: 495265 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6108. Min Act: -0.0000

Data Index: 421564 (C4 (Web Text))

Max Activating Token Index: 860