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

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

Neuron 4055 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8731. Min Range: -6.8731

Max Act: 6.8731. Min Act: -0.0000

Data Index: 559812 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.7452. Min Act: -0.0000

Data Index: 136217 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.9092. Min Act: -0.0000

Data Index: 235554 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.5238. Min Act: -0.0000

Data Index: 548684 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.3881. Min Act: -0.0000

Data Index: 908608 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.5610. Min Act: -0.0000

Data Index: 126529 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.5057. Min Act: -0.0000

Data Index: 42401 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.2903. Min Act: -0.0001

Data Index: 890603 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.4531. Min Act: -0.0000

Data Index: 1050303 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.5709. Min Act: -0.0000

Data Index: 1319901 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.0478. Min Act: -0.0000

Data Index: 406567 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.1453. Min Act: -0.0000

Data Index: 753703 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.3143. Min Act: -0.0000

Data Index: 217578 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.1360. Min Act: -0.0000

Data Index: 618637 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.1015. Min Act: -0.0000

Data Index: 416639 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.1060. Min Act: -0.0000

Data Index: 289113 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.2592. Min Act: -0.0000

Data Index: 884696 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 6.8731. Min Range: -6.8731

Max Act: 4.8616. Min Act: -0.0000

Data Index: 1310142 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 6.8731. Min Range: -6.8731

Max Act: 4.8183. Min Act: -0.0000

Data Index: 488780 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 6.8731. Min Range: -6.8731

Max Act: 5.0092. Min Act: -0.0000

Data Index: 55247 (C4 (Web Text))

Max Activating Token Index: 551