Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3840 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7800. Min Act: -0.0000

Data Index: 456400 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1170315 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7370. Min Act: -0.0000

Data Index: 134938 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7034. Min Act: -0.0000

Data Index: 315274 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1226439 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1258044 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6853. Min Act: -0.0000

Data Index: 224329 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1207974 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6512. Min Act: -0.0000

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1194894 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6333. Min Act: -0.0000

Data Index: 573686 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1341940 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6281. Min Act: -0.0000

Data Index: 833 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5843. Min Act: -0.0000

Data Index: 516930 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5977. Min Act: -0.0000

Data Index: 290560 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5625. Min Act: -0.0000

Data Index: 609321 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5715. Min Act: -0.0000

Data Index: 636755 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5465. Min Act: -0.0000

Data Index: 750535 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5690. Min Act: -0.0000

Data Index: 50441 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5507. Min Act: -0.0000

Data Index: 875669 (C4 (Web Text))

Max Activating Token Index: 743