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

Dataset: The Pile

Neuron 4825 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: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1290193 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1879560 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0527. Min Act: -0.0000

Data Index: 635838 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0493. Min Act: -0.0000

Data Index: 221549 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1369677 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0433. Min Act: -0.0000

Data Index: 40436 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0418. Min Act: -0.0000

Data Index: 913997 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0400. Min Act: -0.0000

Data Index: 477452 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1610574 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0353. Min Act: -0.0000

Data Index: 916801 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1357400 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1214754 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1647013 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1216418 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0306. Min Act: -0.0000

Data Index: 162664 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0305. Min Act: -0.0000

Data Index: 407264 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1804851 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0300. Min Act: -0.0000

Data Index: 742836 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0293. Min Act: -0.0000

Data Index: 446421 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1452827 (The Pile)

Max Activating Token Index: 256