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

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

Neuron 3695 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.9479. Min Act: -0.0001

Data Index: 900491 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6690. Min Act: -0.0001

Data Index: 406399 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6059. Min Act: -0.0001

Data Index: 415620 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5887. Min Act: -0.0001

Data Index: 765579 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6039. Min Act: -0.0001

Data Index: 915215 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5941. Min Act: -0.0001

Data Index: 971681 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5534. Min Act: -0.0001

Data Index: 856796 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5710. Min Act: -0.0001

Data Index: 374625 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1111857 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1233125 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5453. Min Act: -0.0001

Data Index: 280483 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5266. Min Act: -0.0001

Data Index: 1170409 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5404. Min Act: -0.0001

Data Index: 264746 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5595. Min Act: -0.0001

Data Index: 994432 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5561. Min Act: -0.0001

Data Index: 826197 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5524. Min Act: -0.0001

Data Index: 702251 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5505. Min Act: -0.0001

Data Index: 610416 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5621. Min Act: -0.0001

Data Index: 394385 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1266428 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5472. Min Act: -0.0001

Data Index: 1037607 (C4 (Web Text))

Max Activating Token Index: 990