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

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

Neuron 34 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.6864. Min Act: -0.0000

Data Index: 818943 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5947. Min Act: -0.0000

Data Index: 594618 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.6042. Min Act: -0.0000

Data Index: 280445 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5949. Min Act: -0.0000

Data Index: 103232 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5531. Min Act: -0.0000

Data Index: 560619 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5213. Min Act: -0.0000

Data Index: 946613 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1130214 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5078. Min Act: -0.0000

Data Index: 878785 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5200. Min Act: -0.0000

Data Index: 821198 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1068402 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1115017 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4825. Min Act: -0.0000

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4673. Min Act: -0.0000

Data Index: 808877 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4818. Min Act: -0.0000

Data Index: 459556 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4922. Min Act: -0.0000

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4756. Min Act: -0.0000

Data Index: 689167 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4807. Min Act: -0.0000

Data Index: 237255 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4698. Min Act: -0.0000

Data Index: 953044 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1086801 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1058217 (C4 (Web Text))

Max Activating Token Index: 476