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

Dataset: The Pile

Neuron 1571 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: 0.6246. Min Range: -0.6246

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1227760 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4633. Min Act: -0.0000

Data Index: 567131 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1555069 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1259415 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1142999 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1398841 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4317. Min Act: -0.0000

Data Index: 469103 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4642. Min Act: -0.0000

Data Index: 812749 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1732623 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1589116 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4608. Min Act: -0.0000

Data Index: 530850 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4602. Min Act: -0.0000

Data Index: 765093 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4318. Min Act: -0.0000

Data Index: 215223 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4309. Min Act: -0.0000

Data Index: 321442 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4308. Min Act: -0.0000

Data Index: 875471 (The Pile)

Max Activating Token Index: 18

Text #15

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1723555 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1035852 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1763711 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1318372 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1460080 (The Pile)

Max Activating Token Index: 264