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

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

Neuron 326 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: 0.5564. Min Range: -0.5564

Max Act: 0.5564. Min Act: -0.0000

Data Index: 463310 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.5040. Min Act: -0.0000

Data Index: 496817 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1107841 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4892. Min Act: -0.0000

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4946. Min Act: -0.0000

Data Index: 597269 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4752. Min Act: -0.0000

Data Index: 565024 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4512. Min Act: -0.0000

Data Index: 6955 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4629. Min Act: -0.0000

Data Index: 811441 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4578. Min Act: -0.0000

Data Index: 119569 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1068835 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4444. Min Act: -0.0000

Data Index: 662009 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4532. Min Act: -0.0000

Data Index: 767442 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4215. Min Act: -0.0000

Data Index: 688442 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4335. Min Act: -0.0000

Data Index: 410816 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1058625 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1160867 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4264. Min Act: -0.0000

Data Index: 736662 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4204. Min Act: -0.0000

Data Index: 605181 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1324777 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.5564. Min Range: -0.5564

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1201461 (C4 (Web Text))

Max Activating Token Index: 988