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

Dataset: The Pile

Neuron 4176 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: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: 0.0000

Data Index: 1498104 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1208860 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1321514 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0491. Min Act: -0.0000

Data Index: 645153 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0484. Min Act: -0.0000

Data Index: 570995 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0482. Min Act: 0.0000

Data Index: 1897476 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1321354 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0471. Min Act: 0.0000

Data Index: 138294 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0470. Min Act: -0.0000

Data Index: 748348 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0468. Min Act: 0.0000

Data Index: 306449 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1262125 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1464699 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0469. Min Act: 0.0000

Data Index: 1333156 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1103120 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1720811 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1123584 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0464. Min Act: -0.0000

Data Index: 728911 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0464. Min Act: -0.0000

Data Index: 562493 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0464. Min Act: -0.0000

Data Index: 360730 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0463. Min Act: 0.0000

Data Index: 1211980 (The Pile)

Max Activating Token Index: 1023