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

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

Neuron 256 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: 0.1110. Min Range: -0.1110

Max Act: 0.1105. Min Act: -0.0001

Data Index: 376191 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0724. Min Act: -0.0001

Data Index: 285539 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0001

Data Index: 206195 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0890. Min Act: -0.0001

Data Index: 348402 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1346004 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0852. Min Act: -0.0001

Data Index: 794285 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0900. Min Act: -0.0001

Data Index: 266924 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0854. Min Act: -0.0001

Data Index: 473916 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0877. Min Act: -0.0001

Data Index: 270490 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0821. Min Act: -0.0001

Data Index: 666448 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0770. Min Act: -0.0001

Data Index: 27902 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0822. Min Act: -0.0001

Data Index: 3529 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0845. Min Act: -0.0001

Data Index: 573105 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0894. Min Act: -0.0001

Data Index: 803744 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0798. Min Act: -0.0001

Data Index: 805069 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0824. Min Act: -0.0001

Data Index: 978423 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0874. Min Act: -0.0001

Data Index: 754671 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1176871 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0829. Min Act: -0.0001

Data Index: 371385 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0797. Min Act: -0.0001

Data Index: 621052 (C4 (Web Text))

Max Activating Token Index: 88