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

Dataset: The Pile

Neuron 3236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1457119 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5623. Min Act: -0.0000

Data Index: 215306 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6084. Min Act: -0.0000

Data Index: 869249 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5910. Min Act: -0.0000

Data Index: 31386 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1632619 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6181. Min Act: -0.0000

Data Index: 792874 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1369058 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1001278 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1071902 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6404. Min Act: -0.0000

Data Index: 552322 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1277895 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5511. Min Act: -0.0000

Data Index: 963452 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5921. Min Act: -0.0000

Data Index: 983513 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6452. Min Act: -0.0000

Data Index: 988527 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1956346 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1829160 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5462. Min Act: -0.0000

Data Index: 636494 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1122993 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1952325 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5578. Min Act: -0.0000

Data Index: 395552 (The Pile)

Max Activating Token Index: 929