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

Dataset: The Pile

Neuron 187 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1836052 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1044400 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0549. Min Act: -0.0000

Data Index: 945842 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1662818 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0541. Min Act: -0.0000

Data Index: 334423 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1629994 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0514. Min Act: -0.0000

Data Index: 327772 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1005101 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0524. Min Act: -0.0000

Data Index: 588722 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1424437 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1688447 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1576222 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0518. Min Act: -0.0000

Data Index: 232188 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1983732 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1482501 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0510. Min Act: -0.0000

Data Index: 848870 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0509. Min Act: -0.0000

Data Index: 923209 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0000

Data Index: 808714 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0000

Data Index: 144053 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1242923 (The Pile)

Max Activating Token Index: 5