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

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

Neuron 1594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.4260. Min Act: -0.0000

Data Index: 318327 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.3634. Min Act: -0.0000

Data Index: 1141827 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.1699. Min Act: -0.0000

Data Index: 882716 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.2565. Min Act: -0.0000

Data Index: 556001 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.0467. Min Act: -0.0000

Data Index: 247351 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1317151 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 2.4260. Min Range: -2.4260

Max Act: 2.1437. Min Act: -0.0000

Data Index: 20502 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.9053. Min Act: -0.0000

Data Index: 945810 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.7865. Min Act: -0.0000

Data Index: 4555 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1083958 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8792. Min Act: -0.0000

Data Index: 378403 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1242275 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8010. Min Act: -0.0000

Data Index: 905973 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8530. Min Act: -0.0000

Data Index: 616173 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8186. Min Act: -0.0000

Data Index: 569568 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8214. Min Act: -0.0000

Data Index: 168487 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.9074. Min Act: -0.0000

Data Index: 628067 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8214. Min Act: -0.0000

Data Index: 493146 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8030. Min Act: -0.0000

Data Index: 1193552 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 2.4260. Min Range: -2.4260

Max Act: 1.8063. Min Act: -0.0000

Data Index: 843613 (C4 (Web Text))

Max Activating Token Index: 203