Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3198 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0002

Data Index: 352087 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1043. Min Act: -0.0002

Data Index: 667630 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1156712 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1074. Min Act: -0.0002

Data Index: 218458 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1218923 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1035. Min Act: -0.0002

Data Index: 338715 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1037. Min Act: -0.0002

Data Index: 600690 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1348315 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1250850 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1000. Min Act: -0.0001

Data Index: 618886 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1000. Min Act: -0.0002

Data Index: 836837 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0983. Min Act: -0.0002

Data Index: 676892 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0978. Min Act: -0.0001

Data Index: 453407 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0931. Min Act: -0.0002

Data Index: 836570 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0924. Min Act: -0.0001

Data Index: 566748 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0981. Min Act: -0.0001

Data Index: 126531 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0924. Min Act: -0.0002

Data Index: 638 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0929. Min Act: -0.0001

Data Index: 555232 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0928. Min Act: -0.0002

Data Index: 266706 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0924. Min Act: -0.0002

Data Index: 615236 (C4 (Web Text))

Max Activating Token Index: 957