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

Dataset: The Pile

Neuron 2719 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.7726. Min Act: -0.0000

Data Index: 661717 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.8119. Min Act: -0.0000

Data Index: 1723073 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.5921. Min Act: -0.0000

Data Index: 974266 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.4896. Min Act: -0.0000

Data Index: 477074 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.1354. Min Act: -0.0000

Data Index: 886757 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.4221. Min Act: -0.0000

Data Index: 1584798 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.2224. Min Act: -0.0000

Data Index: 125700 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.2047. Min Act: -0.0000

Data Index: 384595 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9672. Min Act: -0.0000

Data Index: 1283761 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.0958. Min Act: -0.0000

Data Index: 67829 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.7821. Min Act: -0.0000

Data Index: 188726 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.0809. Min Act: -0.0000

Data Index: 119763 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.1986. Min Act: -0.0000

Data Index: 1381174 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.8007. Min Act: -0.0000

Data Index: 1819996 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.6854. Min Act: -0.0000

Data Index: 525109 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.0568. Min Act: -0.0000

Data Index: 831159 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.6994. Min Act: -0.0000

Data Index: 1584206 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.8390. Min Act: -0.0000

Data Index: 318541 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.6889. Min Act: -0.0000

Data Index: 215371 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.5609. Min Act: -0.0000

Data Index: 785439 (The Pile)

Max Activating Token Index: 339