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

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

Neuron 2039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0003

Data Index: 1185805 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5930. Min Act: -0.0003

Data Index: 538850 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6060. Min Act: -0.0003

Data Index: 1315041 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5736. Min Act: -0.0003

Data Index: 130368 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5405. Min Act: -0.0003

Data Index: 472631 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5463. Min Act: -0.0003

Data Index: 190052 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5274. Min Act: -0.0003

Data Index: 414122 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5066. Min Act: -0.0003

Data Index: 412818 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4853. Min Act: -0.0003

Data Index: 271033 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5445. Min Act: -0.0003

Data Index: 1169743 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4916. Min Act: -0.0003

Data Index: 995847 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5075. Min Act: -0.0003

Data Index: 428417 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4750. Min Act: -0.0003

Data Index: 1323310 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5120. Min Act: -0.0003

Data Index: 1253855 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4864. Min Act: -0.0003

Data Index: 634461 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5213. Min Act: -0.0003

Data Index: 215393 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5067. Min Act: -0.0003

Data Index: 378329 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5319. Min Act: -0.0003

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4980. Min Act: -0.0003

Data Index: 454646 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4932. Min Act: -0.0003

Data Index: 581753 (C4 (Web Text))

Max Activating Token Index: 116