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

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

Neuron 1181 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0470. Min Range: -1.0470

Max Act: 1.0470. Min Act: -0.0000

Data Index: 697079 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9690. Min Act: -0.0000

Data Index: 572913 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9719. Min Act: -0.0000

Data Index: 320497 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9627. Min Act: -0.0000

Data Index: 563030 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1202758 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1139421 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9250. Min Act: 0.0000

Data Index: 308725 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8817. Min Act: -0.0000

Data Index: 197366 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8731. Min Act: -0.0000

Data Index: 182763 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1232099 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1068187 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7799. Min Act: -0.0000

Data Index: 707170 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8835. Min Act: -0.0000

Data Index: 299103 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8046. Min Act: -0.0000

Data Index: 402847 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7581. Min Act: -0.0000

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1188 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1297092 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1188470 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7520. Min Act: 0.0000

Data Index: 574384 (C4 (Web Text))

Max Activating Token Index: 242