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

Dataset: The Pile

Neuron 4608 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: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0000

Data Index: 794552 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0698. Min Act: -0.0000

Data Index: 301140 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1767544 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1303146 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0599. Min Act: -0.0000

Data Index: 219215 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0586. Min Act: -0.0000

Data Index: 695617 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1518687 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0592. Min Act: -0.0000

Data Index: 351488 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0566. Min Act: -0.0000

Data Index: 347731 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1350390 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0564. Min Act: -0.0000

Data Index: 664098 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1300629 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1234744 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0553. Min Act: -0.0000

Data Index: 805195 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1646460 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1677550 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1864143 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1739738 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1425757 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1129857 (The Pile)

Max Activating Token Index: 913