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

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

Neuron 381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.5453. Min Act: -0.0001

Data Index: 880907 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2876. Min Act: -0.0001

Data Index: 78776 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2960. Min Act: -0.0001

Data Index: 321798 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2631. Min Act: -0.0001

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2501. Min Act: -0.0001

Data Index: 1058547 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2269. Min Act: -0.0001

Data Index: 942312 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2228. Min Act: -0.0001

Data Index: 861714 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2625. Min Act: -0.0001

Data Index: 715562 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1078385 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2200. Min Act: -0.0001

Data Index: 552019 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2377. Min Act: -0.0001

Data Index: 974776 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2263. Min Act: -0.0001

Data Index: 325656 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2356. Min Act: -0.0001

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2471. Min Act: -0.0001

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2010. Min Act: -0.0001

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2113. Min Act: -0.0001

Data Index: 891295 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.2139. Min Act: -0.0001

Data Index: 970387 (C4 (Web Text))

Max Activating Token Index: 381