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

Dataset: The Pile

Neuron 2192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.3320. Min Act: -0.0000

Data Index: 744866 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2316. Min Act: -0.0000

Data Index: 90730 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2436. Min Act: -0.0000

Data Index: 563190 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2351. Min Act: -0.0000

Data Index: 5515 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2072. Min Act: -0.0000

Data Index: 35479 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1752429 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2040. Min Act: -0.0000

Data Index: 903602 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2046. Min Act: -0.0000

Data Index: 688788 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1649350 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1913. Min Act: -0.0000

Data Index: 308631 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1117127 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1818. Min Act: -0.0000

Data Index: 557950 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1786. Min Act: -0.0000

Data Index: 126824 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1139685 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1864. Min Act: -0.0000

Data Index: 561177 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1765479 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1698. Min Act: -0.0000

Data Index: 187456 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1161575 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1557. Min Act: -0.0000

Data Index: 706143 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1563157 (The Pile)

Max Activating Token Index: 582