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

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

Neuron 1335 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.0000

Data Index: 514974 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1592190 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1553619 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6768. Min Act: -0.0000

Data Index: 442771 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6853. Min Act: -0.0000

Data Index: 785731 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6676. Min Act: -0.0000

Data Index: 652695 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6651. Min Act: -0.0000

Data Index: 792316 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6369. Min Act: -0.0000

Data Index: 542640 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6389. Min Act: -0.0000

Data Index: 741723 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1424853 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6290. Min Act: -0.0000

Data Index: 159180 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1163900 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6206. Min Act: -0.0000

Data Index: 237723 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5899. Min Act: -0.0000

Data Index: 364447 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1558329 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6115. Min Act: -0.0000

Data Index: 155927 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1036095 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1291573 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1475610 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6102. Min Act: -0.0000

Data Index: 401056 (C4 (Web Text))

Max Activating Token Index: 662