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

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

Neuron 1435 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: 1.0681. Min Range: -1.0681

Max Act: 1.0681. Min Act: -0.0001

Data Index: 1292037 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0262. Min Act: -0.0002

Data Index: 541541 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0353. Min Act: -0.0002

Data Index: 868127 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9679. Min Act: -0.0002

Data Index: 1098191 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9784. Min Act: -0.0002

Data Index: 1183665 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9718. Min Act: -0.0001

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9297. Min Act: -0.0001

Data Index: 722569 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9189. Min Act: -0.0002

Data Index: 487172 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8853. Min Act: -0.0002

Data Index: 1126999 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9086. Min Act: -0.0002

Data Index: 573651 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9087. Min Act: -0.0002

Data Index: 424202 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9249. Min Act: -0.0002

Data Index: 649991 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8702. Min Act: -0.0002

Data Index: 1148187 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1040501 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9078. Min Act: -0.0001

Data Index: 1222303 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8992. Min Act: -0.0001

Data Index: 167584 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8947. Min Act: -0.0002

Data Index: 727214 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8912. Min Act: -0.0001

Data Index: 989730 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9170. Min Act: -0.0002

Data Index: 929817 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8553. Min Act: -0.0002

Data Index: 829926 (C4 (Web Text))

Max Activating Token Index: 459