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

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

Neuron 544 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: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0002

Data Index: 105837 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1174. Min Act: -0.0001

Data Index: 304287 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1154. Min Act: -0.0002

Data Index: 798240 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1006. Min Act: -0.0002

Data Index: 182293 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0987. Min Act: -0.0001

Data Index: 938658 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1226037 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0977. Min Act: -0.0002

Data Index: 177580 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1194089 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0963. Min Act: -0.0002

Data Index: 625482 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1352991 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1130305 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0991. Min Act: -0.0002

Data Index: 584760 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1060891 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0970. Min Act: -0.0002

Data Index: 557701 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1218986 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1091442 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0907. Min Act: -0.0002

Data Index: 667603 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0918. Min Act: -0.0002

Data Index: 139809 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1316273 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0930. Min Act: -0.0002

Data Index: 825687 (C4 (Web Text))

Max Activating Token Index: 660