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

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

Neuron 71 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9456. Min Act: -0.0001

Data Index: 897143 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1003059 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9819. Min Act: -0.0001

Data Index: 36050 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1213494 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9278. Min Act: -0.0001

Data Index: 14706 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9009. Min Act: -0.0001

Data Index: 395931 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9523. Min Act: -0.0001

Data Index: 321013 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8943. Min Act: -0.0001

Data Index: 456212 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8283. Min Act: -0.0001

Data Index: 284957 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1011933 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8707. Min Act: -0.0001

Data Index: 820353 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8997. Min Act: -0.0001

Data Index: 257937 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8870. Min Act: -0.0001

Data Index: 478592 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8850. Min Act: -0.0000

Data Index: 875395 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8829. Min Act: -0.0001

Data Index: 685650 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8999. Min Act: -0.0001

Data Index: 818647 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8516. Min Act: -0.0001

Data Index: 1283897 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8682. Min Act: -0.0001

Data Index: 245111 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8776. Min Act: -0.0000

Data Index: 906322 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8646. Min Act: -0.0001

Data Index: 955148 (C4 (Web Text))

Max Activating Token Index: 713