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

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

Neuron 1365 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: 0.5899. Min Range: -0.5899

Max Act: 0.5899. Min Act: -0.0000

Data Index: 608047 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4720. Min Act: -0.0000

Data Index: 378161 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4585. Min Act: -0.0000

Data Index: 684320 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4225. Min Act: 0.0000

Data Index: 962324 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4513. Min Act: -0.0000

Data Index: 167650 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4189. Min Act: -0.0000

Data Index: 259984 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3992. Min Act: -0.0000

Data Index: 251723 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4044. Min Act: -0.0000

Data Index: 532032 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1312087 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1072338 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1116797 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1143298 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3872. Min Act: -0.0000

Data Index: 913425 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3827. Min Act: -0.0000

Data Index: 718453 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3940. Min Act: -0.0000

Data Index: 225535 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4064. Min Act: -0.0000

Data Index: 698312 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1344306 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4053. Min Act: -0.0000

Data Index: 578014 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3754. Min Act: -0.0000

Data Index: 69183 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.3864. Min Act: -0.0000

Data Index: 804408 (C4 (Web Text))

Max Activating Token Index: 94