Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0001

Data Index: 244214 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1080. Min Act: -0.0001

Data Index: 261905 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0999. Min Act: -0.0001

Data Index: 833239 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1088719 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0936. Min Act: -0.0001

Data Index: 107152 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1158024 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0993. Min Act: -0.0000

Data Index: 489155 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0974. Min Act: 0.0001

Data Index: 5304 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1205623 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0975. Min Act: 0.0001

Data Index: 527569 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0929. Min Act: -0.0001

Data Index: 775876 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0964. Min Act: -0.0001

Data Index: 138024 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1038706 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0992. Min Act: -0.0001

Data Index: 120458 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1178113 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0947. Min Act: -0.0001

Data Index: 318454 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0935. Min Act: -0.0001

Data Index: 402271 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0936. Min Act: -0.0001

Data Index: 657598 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0961. Min Act: -0.0001

Data Index: 108098 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0927. Min Act: -0.0001

Data Index: 717508 (C4 (Web Text))

Max Activating Token Index: 579