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

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

Neuron 3466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0701. Min Act: -0.0000

Data Index: 914586 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6483. Min Act: -0.0000

Data Index: 942103 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7937. Min Act: -0.0000

Data Index: 994256 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6715. Min Act: -0.0000

Data Index: 236936 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1252950 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6809. Min Act: -0.0000

Data Index: 655408 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5294. Min Act: -0.0000

Data Index: 385299 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6414. Min Act: -0.0000

Data Index: 614897 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6224. Min Act: -0.0000

Data Index: 735928 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.4661. Min Act: -0.0000

Data Index: 105271 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5587. Min Act: -0.0000

Data Index: 536250 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5580. Min Act: -0.0000

Data Index: 481552 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5736. Min Act: -0.0000

Data Index: 57460 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1149962 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5236. Min Act: -0.0000

Data Index: 407473 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1078693 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5481. Min Act: -0.0000

Data Index: 966764 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5265. Min Act: -0.0000

Data Index: 900235 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5400. Min Act: -0.0000

Data Index: 852696 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1216168 (C4 (Web Text))

Max Activating Token Index: 131