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

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

Neuron 594 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: 2.8081. Min Range: -2.8081

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1323662 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.3871. Min Act: -0.0000

Data Index: 567781 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.3776. Min Act: -0.0000

Data Index: 1301221 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.4729. Min Act: -0.0000

Data Index: 542430 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.4049. Min Act: -0.0000

Data Index: 494311 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.5312. Min Act: -0.0000

Data Index: 584727 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.3993. Min Act: -0.0000

Data Index: 101529 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.3047. Min Act: -0.0000

Data Index: 260352 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.3112. Min Act: -0.0000

Data Index: 984986 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.0490. Min Act: -0.0000

Data Index: 309025 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.1618. Min Act: -0.0000

Data Index: 178660 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.0426. Min Act: -0.0000

Data Index: 1072466 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.1412. Min Act: -0.0000

Data Index: 1255344 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.1243. Min Act: -0.0000

Data Index: 576657 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 2.8081. Min Range: -2.8081

Max Act: 1.9121. Min Act: -0.0000

Data Index: 1171140 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.1195. Min Act: -0.0000

Data Index: 158191 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1010176 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.8081. Min Range: -2.8081

Max Act: 1.9886. Min Act: -0.0000

Data Index: 819844 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 2.8081. Min Range: -2.8081

Max Act: 2.2125. Min Act: -0.0000

Data Index: 719954 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.8081. Min Range: -2.8081

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1226750 (C4 (Web Text))

Max Activating Token Index: 152