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

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

Neuron 2854 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.9366. Min Act: -0.0000

Data Index: 734049 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.9544. Min Act: -0.0000

Data Index: 573098 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8781. Min Act: -0.0000

Data Index: 910182 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8255. Min Act: -0.0000

Data Index: 205978 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8357. Min Act: -0.0000

Data Index: 914220 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8106. Min Act: -0.0000

Data Index: 152757 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1007989 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8677. Min Act: -0.0000

Data Index: 447035 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1127757 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7082. Min Act: -0.0000

Data Index: 90720 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7670. Min Act: -0.0000

Data Index: 758027 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7932. Min Act: -0.0000

Data Index: 259773 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7525. Min Act: -0.0000

Data Index: 528920 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7399. Min Act: -0.0000

Data Index: 355676 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7269. Min Act: -0.0000

Data Index: 194943 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1187917 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.6812. Min Act: -0.0000

Data Index: 513508 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7279. Min Act: -0.0000

Data Index: 404265 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.6997. Min Act: -0.0000

Data Index: 313852 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1317397 (C4 (Web Text))

Max Activating Token Index: 196