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

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

Neuron 4498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.9130. Min Act: -0.0001

Data Index: 1319061 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.7657. Min Act: -0.0001

Data Index: 1616764 (Python Code)

Max Activating Token Index: 184

Text #2

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1586663 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.7774. Min Act: -0.0001

Data Index: 1537390 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5687. Min Act: -0.0001

Data Index: 1423549 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5776. Min Act: -0.0001

Data Index: 1419425 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6669. Min Act: -0.0001

Data Index: 1601189 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.7591. Min Act: -0.0001

Data Index: 1405504 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.7680. Min Act: -0.0001

Data Index: 1651318 (Python Code)

Max Activating Token Index: 309

Text #9

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1191199 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5584. Min Act: -0.0000

Data Index: 442014 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6475. Min Act: -0.0001

Data Index: 1438880 (Python Code)

Max Activating Token Index: 262

Text #12

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6343. Min Act: -0.0000

Data Index: 532186 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6019. Min Act: -0.0001

Data Index: 1451920 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5330. Min Act: -0.0001

Data Index: 1473376 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6120. Min Act: -0.0001

Data Index: 1508681 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5128. Min Act: -0.0000

Data Index: 546198 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5037. Min Act: -0.0001

Data Index: 1585612 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.6691. Min Act: -0.0001

Data Index: 1508460 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.5742. Min Act: -0.0001

Data Index: 1477488 (Python Code)

Max Activating Token Index: 173