Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1210 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.2174. Min Act: -0.0006

Data Index: 1001387 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1999. Min Act: -0.0006

Data Index: 38472 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1835. Min Act: -0.0006

Data Index: 1324487 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1972. Min Act: -0.0006

Data Index: 188636 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1870. Min Act: -0.0006

Data Index: 177677 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1930. Min Act: -0.0006

Data Index: 388305 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1893. Min Act: -0.0006

Data Index: 1187394 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.2030. Min Act: -0.0006

Data Index: 287686 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1857. Min Act: -0.0006

Data Index: 248109 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1872. Min Act: -0.0006

Data Index: 1075386 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1781. Min Act: -0.0006

Data Index: 502969 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1858. Min Act: -0.0006

Data Index: 448658 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1922. Min Act: -0.0006

Data Index: 1200487 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1842. Min Act: -0.0006

Data Index: 1278645 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1837. Min Act: -0.0006

Data Index: 1000130 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1769. Min Act: -0.0006

Data Index: 411093 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1696. Min Act: -0.0006

Data Index: 622739 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1758. Min Act: -0.0006

Data Index: 599231 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1809. Min Act: -0.0006

Data Index: 307994 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1733. Min Act: -0.0006

Data Index: 1019211 (C4 (Web Text))

Max Activating Token Index: 664