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

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

Neuron 3595 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: 0.7736. Min Range: -0.7736

Max Act: 0.7736. Min Act: -0.0000

Data Index: 200994 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.7728. Min Act: -0.0001

Data Index: 176254 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.7323. Min Act: -0.0001

Data Index: 1356682 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.6936. Min Act: -0.0001

Data Index: 378974 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.7023. Min Act: -0.0000

Data Index: 131930 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1001105 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1160998 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.6232. Min Act: -0.0000

Data Index: 170934 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5751. Min Act: -0.0000

Data Index: 304060 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5831. Min Act: -0.0000

Data Index: 60340 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5342. Min Act: -0.0000

Data Index: 759535 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1122076 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5291. Min Act: -0.0001

Data Index: 193026 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5580. Min Act: -0.0000

Data Index: 792647 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5612. Min Act: -0.0000

Data Index: 286863 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5509. Min Act: -0.0000

Data Index: 186217 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5346. Min Act: -0.0000

Data Index: 710686 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1047701 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5497. Min Act: -0.0000

Data Index: 726259 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.7736. Min Range: -0.7736

Max Act: 0.5329. Min Act: -0.0000

Data Index: 822344 (C4 (Web Text))

Max Activating Token Index: 54