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

Dataset: The Pile

Neuron 16 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2889. Min Act: -0.0000

Data Index: 869113 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2912. Min Act: -0.0000

Data Index: 27102 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1448248 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1500007 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2874. Min Act: -0.0000

Data Index: 390434 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2536. Min Act: -0.0000

Data Index: 833693 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1676174 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1388222 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1253136 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1563723 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2407. Min Act: -0.0000

Data Index: 955271 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1946915 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2389. Min Act: -0.0000

Data Index: 602666 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1278963 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2128. Min Act: -0.0000

Data Index: 900789 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2097. Min Act: -0.0000

Data Index: 268479 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1972. Min Act: -0.0000

Data Index: 592921 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2135. Min Act: -0.0000

Data Index: 291744 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1802370 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1684716 (The Pile)

Max Activating Token Index: 192