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

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

Neuron 3977 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: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 625977 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1168114 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1136778 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1092. Min Act: -0.0001

Data Index: 734780 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1030. Min Act: -0.0001

Data Index: 608477 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0931. Min Act: -0.0002

Data Index: 719359 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0965. Min Act: -0.0002

Data Index: 212186 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0854. Min Act: -0.0002

Data Index: 90159 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1184690 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0892. Min Act: -0.0002

Data Index: 101783 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0912. Min Act: -0.0001

Data Index: 987925 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0899. Min Act: -0.0001

Data Index: 907451 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0901. Min Act: -0.0001

Data Index: 652047 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0922. Min Act: -0.0001

Data Index: 609947 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0837. Min Act: -0.0001

Data Index: 491375 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0874. Min Act: -0.0002

Data Index: 775629 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0902. Min Act: -0.0002

Data Index: 762888 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0904. Min Act: -0.0002

Data Index: 674972 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0900. Min Act: -0.0002

Data Index: 110117 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0867. Min Act: -0.0001

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 301