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

Dataset: The Pile

Neuron 2566 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: 5.4106. Min Range: -5.4106

Max Act: 5.3533. Min Act: -0.0000

Data Index: 1085146 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 5.4106. Min Range: -5.4106

Max Act: 5.4106. Min Act: -0.0000

Data Index: 280432 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 5.4106. Min Range: -5.4106

Max Act: 5.0355. Min Act: -0.0000

Data Index: 1080701 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 5.4106. Min Range: -5.4106

Max Act: 5.1934. Min Act: -0.0000

Data Index: 800960 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.6536. Min Act: -0.0000

Data Index: 268383 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.8072. Min Act: -0.0000

Data Index: 1186190 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.5956. Min Act: -0.0000

Data Index: 1692413 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.5627. Min Act: -0.0000

Data Index: 848818 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.3116. Min Act: 0.0000

Data Index: 1733357 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.7545. Min Act: -0.0000

Data Index: 753525 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.6319. Min Act: -0.0000

Data Index: 350585 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.0652. Min Act: -0.0000

Data Index: 723878 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.8065. Min Act: -0.0000

Data Index: 778743 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.9743. Min Act: -0.0000

Data Index: 1746990 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 5.4106. Min Range: -5.4106

Max Act: 4.1042. Min Act: -0.0000

Data Index: 1223126 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.6747. Min Act: -0.0000

Data Index: 708662 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.6672. Min Act: -0.0000

Data Index: 326277 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.8237. Min Act: -0.0000

Data Index: 1850174 (The Pile)

Max Activating Token Index: 827

Text #18

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.8468. Min Act: -0.0000

Data Index: 573415 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 5.4106. Min Range: -5.4106

Max Act: 3.7783. Min Act: -0.0000

Data Index: 169541 (The Pile)

Max Activating Token Index: 814