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

Dataset: The Pile

Neuron 650 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: 0.0691. Min Range: -0.0691

Max Act: 0.0691. Min Act: -0.0000

Data Index: 278432 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0539. Min Act: -0.0000

Data Index: 541257 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1627695 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0519. Min Act: -0.0000

Data Index: 164970 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0517. Min Act: -0.0000

Data Index: 946977 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1445260 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1777708 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0506. Min Act: -0.0000

Data Index: 886764 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1189409 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1212528 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1773816 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1403284 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1798657 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0499. Min Act: -0.0000

Data Index: 18448 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1100539 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1525960 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0493. Min Act: -0.0000

Data Index: 913690 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0490. Min Act: -0.0000

Data Index: 526291 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1972504 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1800702 (The Pile)

Max Activating Token Index: 1023