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

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

Neuron 742 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0006

Data Index: 1223725 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1009. Min Act: -0.0006

Data Index: 164688 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1010. Min Act: -0.0006

Data Index: 1093963 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0931. Min Act: -0.0006

Data Index: 735214 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0932. Min Act: -0.0006

Data Index: 81294 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0920. Min Act: -0.0006

Data Index: 876452 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0913. Min Act: -0.0006

Data Index: 1219658 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0933. Min Act: -0.0006

Data Index: 733285 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0861. Min Act: -0.0006

Data Index: 1204447 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0927. Min Act: -0.0006

Data Index: 536071 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0919. Min Act: -0.0006

Data Index: 676738 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0954. Min Act: -0.0006

Data Index: 748063 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0913. Min Act: -0.0006

Data Index: 599720 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0868. Min Act: -0.0006

Data Index: 888044 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0899. Min Act: -0.0006

Data Index: 237277 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0931. Min Act: -0.0006

Data Index: 341705 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0920. Min Act: -0.0006

Data Index: 1208826 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0920. Min Act: -0.0006

Data Index: 582982 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0851. Min Act: -0.0006

Data Index: 757384 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0846. Min Act: -0.0006

Data Index: 791939 (C4 (Web Text))

Max Activating Token Index: 73