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

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

Neuron 3588 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.9199. Min Act: -0.0001

Data Index: 310941 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.9105. Min Act: -0.0001

Data Index: 39947 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.9049. Min Act: -0.0002

Data Index: 459343 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.8726. Min Act: -0.0002

Data Index: 837065 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.8858. Min Act: -0.0002

Data Index: 621410 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7347. Min Act: -0.0002

Data Index: 243114 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.8550. Min Act: -0.0001

Data Index: 194461 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.8042. Min Act: -0.0001

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7609. Min Act: -0.0002

Data Index: 276607 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.8250. Min Act: -0.0002

Data Index: 707951 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1165617 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1086486 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7806. Min Act: -0.0002

Data Index: 1290538 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7906. Min Act: -0.0001

Data Index: 613614 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7036. Min Act: -0.0002

Data Index: 904815 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7875. Min Act: -0.0001

Data Index: 785320 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7306. Min Act: -0.0002

Data Index: 659972 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7344. Min Act: -0.0001

Data Index: 56616 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7465. Min Act: -0.0002

Data Index: 618825 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.9199. Min Range: -0.9199

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1320233 (C4 (Web Text))

Max Activating Token Index: 398