Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4832. Min Act: -0.0001

Data Index: 620708 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4792. Min Act: -0.0001

Data Index: 417384 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4694. Min Act: -0.0001

Data Index: 83076 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4561. Min Act: -0.0001

Data Index: 970981 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4553. Min Act: -0.0001

Data Index: 214848 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1269338 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4695. Min Act: -0.0001

Data Index: 221275 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4190. Min Act: -0.0001

Data Index: 860351 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4163. Min Act: -0.0001

Data Index: 77031 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3781. Min Act: -0.0001

Data Index: 784080 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1112079 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1017732 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3990. Min Act: -0.0001

Data Index: 1270530 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1290744 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3805. Min Act: -0.0001

Data Index: 417267 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1002395 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4052. Min Act: -0.0001

Data Index: 690525 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3797. Min Act: -0.0001

Data Index: 1156667 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3862. Min Act: -0.0001

Data Index: 695045 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3873. Min Act: -0.0001

Data Index: 407267 (C4 (Web Text))

Max Activating Token Index: 222