Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1258 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1353875 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1063. Min Act: -0.0002

Data Index: 964666 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1047. Min Act: -0.0002

Data Index: 467495 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1119186 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1194327 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0980. Min Act: -0.0002

Data Index: 843581 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0992. Min Act: -0.0002

Data Index: 664362 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0969. Min Act: -0.0002

Data Index: 978788 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0953. Min Act: -0.0002

Data Index: 186869 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0977. Min Act: -0.0002

Data Index: 616701 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1102957 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0961. Min Act: -0.0002

Data Index: 224632 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0942. Min Act: -0.0002

Data Index: 321348 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1263671 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1261673 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0948. Min Act: -0.0002

Data Index: 957326 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1196977 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0928. Min Act: -0.0002

Data Index: 483318 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1338150 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0944. Min Act: -0.0002

Data Index: 910936 (C4 (Web Text))

Max Activating Token Index: 952