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

Dataset: The Pile

Neuron 2919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.3511. Min Act: -0.0000

Data Index: 533846 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.2606. Min Act: -0.0000

Data Index: 710196 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1793218 (The Pile)

Max Activating Token Index: 72

Text #3

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1875178 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1397875 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1211370 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1920901 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9415. Min Act: -0.0000

Data Index: 923816 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9318. Min Act: -0.0000

Data Index: 48248 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1636284 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0096. Min Act: -0.0000

Data Index: 684262 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1654657 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0006. Min Act: -0.0000

Data Index: 930923 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1911924 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1910571 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9983. Min Act: 0.0000

Data Index: 1336396 (The Pile)

Max Activating Token Index: 689

Text #16

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1642013 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1768938 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.8699. Min Act: -0.0000

Data Index: 30314 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9104. Min Act: -0.0000

Data Index: 805158 (The Pile)

Max Activating Token Index: 295