Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2502 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.9901. Min Act: -0.0000

Data Index: 138119 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8242. Min Act: -0.0000

Data Index: 932972 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8027. Min Act: -0.0001

Data Index: 517611 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8248. Min Act: -0.0000

Data Index: 51547 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8252. Min Act: -0.0001

Data Index: 435296 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.6909. Min Act: -0.0001

Data Index: 1119458 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8057. Min Act: -0.0000

Data Index: 783542 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1237526 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.8004. Min Act: -0.0000

Data Index: 1259243 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.6722. Min Act: -0.0000

Data Index: 557907 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.6050. Min Act: -0.0001

Data Index: 1049675 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.6550. Min Act: -0.0000

Data Index: 483360 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.3971. Min Act: -0.0000

Data Index: 465783 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1134033 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.5428. Min Act: -0.0001

Data Index: 997857 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.4380. Min Act: -0.0000

Data Index: 599062 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1316447 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.4921. Min Act: -0.0000

Data Index: 541089 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.6704. Min Act: -0.0000

Data Index: 824816 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.9901. Min Range: -1.9901

Max Act: 1.5108. Min Act: -0.0000

Data Index: 144345 (C4 (Web Text))

Max Activating Token Index: 96