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

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

Neuron 604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0194. Min Range: -1.0194

Max Act: 1.0194. Min Act: -0.0001

Data Index: 730058 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8800. Min Act: -0.0001

Data Index: 218249 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8956. Min Act: -0.0001

Data Index: 207819 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8824. Min Act: -0.0001

Data Index: 1036874 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7952. Min Act: -0.0001

Data Index: 693736 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8639. Min Act: -0.0001

Data Index: 702577 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8662. Min Act: -0.0001

Data Index: 793400 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8117. Min Act: -0.0001

Data Index: 57809 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1301351 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.5618. Min Act: -0.0001

Data Index: 1091701 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7485. Min Act: -0.0001

Data Index: 521826 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7042. Min Act: -0.0001

Data Index: 577340 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6260. Min Act: -0.0001

Data Index: 872417 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6384. Min Act: -0.0001

Data Index: 483531 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6953. Min Act: -0.0001

Data Index: 30607 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6664. Min Act: -0.0001

Data Index: 743841 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7202. Min Act: -0.0001

Data Index: 693357 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6716. Min Act: -0.0001

Data Index: 1135627 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6867. Min Act: -0.0001

Data Index: 765681 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7253. Min Act: -0.0001

Data Index: 283949 (C4 (Web Text))

Max Activating Token Index: 216