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

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

Neuron 3181 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0542. Min Range: -1.0542

Max Act: 1.0542. Min Act: -0.0000

Data Index: 44028 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9214. Min Act: -0.0000

Data Index: 198374 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1248939 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1074905 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8447. Min Act: -0.0000

Data Index: 753671 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1107160 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8852. Min Act: -0.0000

Data Index: 662182 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1284957 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9010. Min Act: -0.0000

Data Index: 84855 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1104931 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8072. Min Act: -0.0000

Data Index: 465061 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8173. Min Act: -0.0000

Data Index: 731720 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1033836 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8004. Min Act: -0.0000

Data Index: 552015 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8573. Min Act: -0.0000

Data Index: 335332 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7638. Min Act: -0.0000

Data Index: 414014 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1606010 (Python Code)

Max Activating Token Index: 539

Text #17

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7919. Min Act: -0.0000

Data Index: 768075 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8398. Min Act: -0.0000

Data Index: 800567 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1140605 (C4 (Web Text))

Max Activating Token Index: 260