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

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

Neuron 2429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4798. Min Range: -5.4798

Max Act: 5.4798. Min Act: -0.0000

Data Index: 519371 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 5.4798. Min Range: -5.4798

Max Act: 5.0996. Min Act: -0.0000

Data Index: 571758 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 5.4798. Min Range: -5.4798

Max Act: 5.0977. Min Act: -0.0000

Data Index: 1188721 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.3866. Min Act: -0.0000

Data Index: 666009 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.9255. Min Act: -0.0000

Data Index: 1106013 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.6658. Min Act: -0.0000

Data Index: 768757 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.4918. Min Act: -0.0000

Data Index: 106965 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.5800. Min Act: -0.0000

Data Index: 890037 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.3943. Min Act: -0.0000

Data Index: 1160733 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.9830. Min Act: -0.0000

Data Index: 264060 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.2733. Min Act: -0.0000

Data Index: 631908 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.0180. Min Act: -0.0000

Data Index: 523686 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.0842. Min Act: -0.0000

Data Index: 434164 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 5.4798. Min Range: -5.4798

Max Act: 4.0562. Min Act: -0.0000

Data Index: 612229 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.9742. Min Act: -0.0000

Data Index: 649370 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.7402. Min Act: -0.0000

Data Index: 511228 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.6889. Min Act: -0.0000

Data Index: 336304 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.5868. Min Act: -0.0000

Data Index: 865052 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.6193. Min Act: -0.0000

Data Index: 639204 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 5.4798. Min Range: -5.4798

Max Act: 3.4208. Min Act: -0.0000

Data Index: 122219 (C4 (Web Text))

Max Activating Token Index: 835