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

Dataset: The Pile

Neuron 1841 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3969. Min Act: -0.0000

Data Index: 871428 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1787955 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3638. Min Act: -0.0000

Data Index: 286504 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3546. Min Act: -0.0000

Data Index: 731434 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.4013. Min Act: -0.0000

Data Index: 957479 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3726. Min Act: -0.0000

Data Index: 555623 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1473312 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1546489 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1476121 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1135227 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1898915 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3823. Min Act: -0.0000

Data Index: 291006 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3129. Min Act: -0.0000

Data Index: 807979 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3209. Min Act: -0.0000

Data Index: 682235 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1350235 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3252. Min Act: -0.0000

Data Index: 434666 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1885633 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1234927 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1306672 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3510. Min Act: -0.0000

Data Index: 667423 (The Pile)

Max Activating Token Index: 173