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

Dataset: The Pile

Neuron 453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0921. Min Range: -1.0921

Max Act: 1.0921. Min Act: -0.0000

Data Index: 471275 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 1.0921. Min Range: -1.0921

Max Act: 1.0013. Min Act: -0.0000

Data Index: 670592 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 1.0921. Min Range: -1.0921

Max Act: 1.0399. Min Act: -0.0000

Data Index: 500819 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9985. Min Act: -0.0000

Data Index: 581195 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9426. Min Act: -0.0000

Data Index: 185216 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9663. Min Act: -0.0000

Data Index: 277750 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9486. Min Act: -0.0000

Data Index: 877311 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9268. Min Act: -0.0000

Data Index: 101784 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1715794 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1468629 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1466698 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8844. Min Act: -0.0000

Data Index: 439359 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1569555 (The Pile)

Max Activating Token Index: 952

Text #13

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9086. Min Act: -0.0000

Data Index: 693554 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.9077. Min Act: -0.0000

Data Index: 665356 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8267. Min Act: -0.0000

Data Index: 363999 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8644. Min Act: -0.0000

Data Index: 254966 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8621. Min Act: -0.0000

Data Index: 47781 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8908. Min Act: -0.0000

Data Index: 752378 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 1.0921. Min Range: -1.0921

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1500353 (The Pile)

Max Activating Token Index: 991