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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.5709. Min Act: -0.0000

Data Index: 852727 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.4487. Min Act: -0.0000

Data Index: 432094 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.5405. Min Act: -0.0000

Data Index: 889796 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.4589. Min Act: -0.0000

Data Index: 1287113 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3932. Min Act: -0.0000

Data Index: 130592 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3184. Min Act: -0.0000

Data Index: 92762 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3929. Min Act: -0.0000

Data Index: 559341 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1099003 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1236573 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3810. Min Act: -0.0000

Data Index: 610502 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.2791. Min Act: -0.0000

Data Index: 988562 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1266317 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.2624. Min Act: -0.0000

Data Index: 516075 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1516. Min Act: -0.0000

Data Index: 104759 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1838. Min Act: -0.0000

Data Index: 494418 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1228969 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1100872 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1860. Min Act: -0.0000

Data Index: 935303 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1246276 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1619. Min Act: -0.0000

Data Index: 504900 (C4 (Web Text))

Max Activating Token Index: 596