Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1162. Min Act: -0.0001

Data Index: 54240 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0996. Min Act: -0.0001

Data Index: 43243 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0875. Min Act: -0.0001

Data Index: 413428 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0876. Min Act: -0.0001

Data Index: 592996 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0885. Min Act: -0.0001

Data Index: 737200 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0841. Min Act: -0.0001

Data Index: 409255 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0786. Min Act: -0.0001

Data Index: 866928 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0751. Min Act: -0.0001

Data Index: 506813 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0822. Min Act: -0.0001

Data Index: 388003 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0801. Min Act: -0.0001

Data Index: 946673 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1107012 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0780. Min Act: -0.0001

Data Index: 436213 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1998 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1172931 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0771. Min Act: -0.0001

Data Index: 334626 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0755. Min Act: -0.0001

Data Index: 643571 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0726. Min Act: -0.0001

Data Index: 536954 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0736. Min Act: -0.0001

Data Index: 966612 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1167175 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1090190 (C4 (Web Text))

Max Activating Token Index: 61