Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 50 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0999. Min Act: -0.0004

Data Index: 675819 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0004

Data Index: 1323343 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0922. Min Act: -0.0004

Data Index: 130838 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0927. Min Act: -0.0004

Data Index: 1240308 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0919. Min Act: -0.0004

Data Index: 475001 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0824. Min Act: -0.0004

Data Index: 8067 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0842. Min Act: -0.0004

Data Index: 805976 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0874. Min Act: -0.0004

Data Index: 450179 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0734. Min Act: -0.0004

Data Index: 961162 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0823. Min Act: -0.0004

Data Index: 1300367 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0769. Min Act: -0.0004

Data Index: 54363 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0774. Min Act: -0.0004

Data Index: 353774 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0799. Min Act: -0.0004

Data Index: 1084037 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0798. Min Act: -0.0004

Data Index: 1006162 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0796. Min Act: -0.0004

Data Index: 885254 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0762. Min Act: -0.0004

Data Index: 1271521 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0792. Min Act: -0.0004

Data Index: 1288236 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0791. Min Act: -0.0004

Data Index: 1098207 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0792. Min Act: -0.0004

Data Index: 1338119 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0759. Min Act: -0.0004

Data Index: 1316772 (C4 (Web Text))

Max Activating Token Index: 891