Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3930 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0002

Data Index: 2744 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1673 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0967. Min Act: -0.0002

Data Index: 574131 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0981. Min Act: -0.0002

Data Index: 453653 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1196963 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1239949 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0950. Min Act: -0.0002

Data Index: 821912 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1300300 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0920. Min Act: -0.0002

Data Index: 256734 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0923. Min Act: -0.0002

Data Index: 399325 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0937. Min Act: -0.0002

Data Index: 575540 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1307175 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1301301 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1274886 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0902. Min Act: -0.0002

Data Index: 513728 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0920. Min Act: -0.0002

Data Index: 954809 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0897. Min Act: -0.0002

Data Index: 682914 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0910. Min Act: -0.0002

Data Index: 972272 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1231004 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1263802 (C4 (Web Text))

Max Activating Token Index: 22