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

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

Neuron 2840 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: 0.4782. Min Range: -0.4782

Max Act: 0.4782. Min Act: -0.0000

Data Index: 668499 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4708. Min Act: -0.0000

Data Index: 300775 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4750. Min Act: -0.0000

Data Index: 93288 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4068. Min Act: -0.0000

Data Index: 662440 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4410. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3944. Min Act: -0.0000

Data Index: 650971 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3891. Min Act: -0.0000

Data Index: 895127 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1189161 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4067. Min Act: -0.0000

Data Index: 667581 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3812. Min Act: -0.0000

Data Index: 446067 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3611. Min Act: -0.0000

Data Index: 766666 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1356809 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3451. Min Act: 0.0000

Data Index: 541749 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3483. Min Act: 0.0001

Data Index: 421867 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3413. Min Act: -0.0000

Data Index: 244206 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1057941 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1166497 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3325. Min Act: -0.0000

Data Index: 454407 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3427. Min Act: -0.0000

Data Index: 600039 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3477. Min Act: -0.0000

Data Index: 552348 (C4 (Web Text))

Max Activating Token Index: 332