Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9907. Min Act: -0.0000

Data Index: 928878 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7648. Min Act: -0.0000

Data Index: 360098 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7333. Min Act: -0.0000

Data Index: 122400 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1410399 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7196. Min Act: -0.0000

Data Index: 600949 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7649. Min Act: -0.0000

Data Index: 134660 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7110. Min Act: -0.0000

Data Index: 740318 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7494. Min Act: -0.0000

Data Index: 921325 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1290554 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5997. Min Act: -0.0000

Data Index: 53362 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7139. Min Act: -0.0000

Data Index: 774742 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5031. Min Act: -0.0000

Data Index: 756295 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1199471 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1976351 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.6206. Min Act: -0.0000

Data Index: 602153 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.3923. Min Act: -0.0000

Data Index: 911246 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5573. Min Act: -0.0000

Data Index: 948312 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1348285 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1963475 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1117709 (The Pile)

Max Activating Token Index: 195