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

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

Neuron 3111 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3399. Min Act: -0.0001

Data Index: 464491 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1356724 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2208. Min Act: -0.0001

Data Index: 50930 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1941. Min Act: -0.0001

Data Index: 913013 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1946. Min Act: -0.0001

Data Index: 965383 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1132769 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1129532 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1945. Min Act: -0.0001

Data Index: 678234 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2023. Min Act: -0.0001

Data Index: 821791 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1942. Min Act: -0.0001

Data Index: 826730 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1141682 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1052927 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1829. Min Act: -0.0001

Data Index: 543646 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1809. Min Act: -0.0001

Data Index: 186631 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1191286 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1656. Min Act: -0.0001

Data Index: 475370 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1893. Min Act: -0.0001

Data Index: 492192 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1630. Min Act: -0.0001

Data Index: 940158 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1717. Min Act: -0.0001

Data Index: 22616 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.1614. Min Act: -0.0001

Data Index: 426704 (C4 (Web Text))

Max Activating Token Index: 199