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

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

Neuron 576 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.8061. Min Act: -0.0002

Data Index: 533881 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7395. Min Act: -0.0002

Data Index: 401276 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6966. Min Act: -0.0002

Data Index: 283865 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6509. Min Act: -0.0002

Data Index: 687971 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6873. Min Act: -0.0002

Data Index: 960553 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7178. Min Act: -0.0002

Data Index: 1129404 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6878. Min Act: -0.0002

Data Index: 358349 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6771. Min Act: -0.0002

Data Index: 783278 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7104. Min Act: -0.0002

Data Index: 582727 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7085. Min Act: -0.0002

Data Index: 1323181 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6205. Min Act: -0.0002

Data Index: 150875 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7079. Min Act: -0.0002

Data Index: 35625 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6611. Min Act: -0.0002

Data Index: 1194501 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6352. Min Act: -0.0002

Data Index: 518504 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6531. Min Act: -0.0002

Data Index: 1337004 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6953. Min Act: -0.0002

Data Index: 1153117 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6267. Min Act: -0.0002

Data Index: 331264 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6733. Min Act: -0.0002

Data Index: 122918 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6468. Min Act: -0.0002

Data Index: 1299410 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6250. Min Act: -0.0002

Data Index: 419531 (C4 (Web Text))

Max Activating Token Index: 251