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

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

Neuron 4753 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: 0.6207. Min Range: -0.6207

Max Act: 0.6180. Min Act: -0.0000

Data Index: 312796 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1075351 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6068. Min Act: -0.0000

Data Index: 700608 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5995. Min Act: -0.0000

Data Index: 208325 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5573. Min Act: -0.0000

Data Index: 970123 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1025874 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5201. Min Act: -0.0000

Data Index: 32001 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5294. Min Act: -0.0000

Data Index: 835050 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5127. Min Act: -0.0000

Data Index: 22081 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4817. Min Act: -0.0000

Data Index: 106215 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4793. Min Act: -0.0000

Data Index: 63260 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4928. Min Act: -0.0000

Data Index: 667562 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5112. Min Act: -0.0000

Data Index: 107300 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1062499 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4764. Min Act: -0.0000

Data Index: 637580 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1291767 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4900. Min Act: -0.0000

Data Index: 119173 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4586. Min Act: -0.0000

Data Index: 706516 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4606. Min Act: -0.0000

Data Index: 261470 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1098693 (C4 (Web Text))

Max Activating Token Index: 761