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

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

Neuron 5062 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: 1.6169. Min Range: -1.6169

Max Act: 1.5121. Min Act: -0.0000

Data Index: 429982 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4902. Min Act: -0.0000

Data Index: 494395 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.6169. Min Act: -0.0000

Data Index: 966954 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1120008 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1249114 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1151440 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4433. Min Act: -0.0000

Data Index: 644432 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4116. Min Act: -0.0000

Data Index: 559920 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3845. Min Act: -0.0000

Data Index: 626730 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3103. Min Act: -0.0000

Data Index: 20692 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3787. Min Act: -0.0000

Data Index: 662397 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3110. Min Act: 0.0000

Data Index: 203101 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1138771 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3366. Min Act: -0.0000

Data Index: 678217 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3414. Min Act: 0.0000

Data Index: 396742 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3274. Min Act: -0.0000

Data Index: 75174 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2972. Min Act: -0.0000

Data Index: 737024 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3421. Min Act: -0.0000

Data Index: 464632 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3235. Min Act: -0.0000

Data Index: 560763 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2622. Min Act: -0.0000

Data Index: 139673 (C4 (Web Text))

Max Activating Token Index: 906