Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.1046. Min Range: -7.1046

Max Act: 7.1046. Min Act: -0.0000

Data Index: 1915774 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.3330. Min Act: -0.0000

Data Index: 1372082 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.4593. Min Act: -0.0000

Data Index: 1222835 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.4382. Min Act: -0.0000

Data Index: 1828016 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.6062. Min Act: -0.0000

Data Index: 206553 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.6192. Min Act: -0.0000

Data Index: 326100 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.5915. Min Act: -0.0000

Data Index: 983784 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.1125. Min Act: -0.0000

Data Index: 1970952 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.5444. Min Act: -0.0000

Data Index: 1812090 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.0686. Min Act: -0.0000

Data Index: 481634 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.2381. Min Act: -0.0000

Data Index: 1186289 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.0720. Min Act: -0.0000

Data Index: 1326965 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.0308. Min Act: -0.0000

Data Index: 339974 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.9649. Min Act: -0.0000

Data Index: 957720 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 7.1046. Min Range: -7.1046

Max Act: 6.1717. Min Act: 0.0001

Data Index: 1023047 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.7830. Min Act: -0.0000

Data Index: 464874 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.7743. Min Act: -0.0000

Data Index: 1645263 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.9499. Min Act: -0.0000

Data Index: 1314792 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.9358. Min Act: -0.0000

Data Index: 423685 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 7.1046. Min Range: -7.1046

Max Act: 5.7527. Min Act: -0.0000

Data Index: 52788 (The Pile)

Max Activating Token Index: 162