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

Dataset: The Pile

Neuron 1630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1716177 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4430. Min Act: -0.0000

Data Index: 423690 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4393. Min Act: -0.0000

Data Index: 363504 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4223. Min Act: -0.0000

Data Index: 34418 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4036. Min Act: -0.0000

Data Index: 605711 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1681755 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1684585 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1313927 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1306940 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3762. Min Act: -0.0000

Data Index: 344003 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4020. Min Act: -0.0000

Data Index: 906808 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1672703 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3798. Min Act: -0.0000

Data Index: 197011 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1345948 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1388071 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3853. Min Act: -0.0000

Data Index: 295158 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3873. Min Act: -0.0000

Data Index: 13478 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1515671 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3778. Min Act: -0.0000

Data Index: 934960 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3767. Min Act: -0.0000

Data Index: 169563 (The Pile)

Max Activating Token Index: 295