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

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

Neuron 3850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8936. Min Act: -0.0002

Data Index: 666176 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8851. Min Act: -0.0002

Data Index: 581758 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8527. Min Act: -0.0001

Data Index: 771662 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8471. Min Act: -0.0001

Data Index: 1162536 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8318. Min Act: -0.0002

Data Index: 1108425 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8208. Min Act: -0.0001

Data Index: 775752 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8265. Min Act: -0.0002

Data Index: 287348 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8410. Min Act: -0.0002

Data Index: 775350 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8357. Min Act: -0.0001

Data Index: 1219099 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8006. Min Act: -0.0001

Data Index: 412006 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7735. Min Act: -0.0001

Data Index: 290459 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7521. Min Act: -0.0002

Data Index: 1305645 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8426. Min Act: -0.0002

Data Index: 189637 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7547. Min Act: -0.0002

Data Index: 1115575 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7310. Min Act: -0.0001

Data Index: 1043485 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7331. Min Act: -0.0001

Data Index: 350976 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8098. Min Act: -0.0002

Data Index: 269953 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7108. Min Act: -0.0001

Data Index: 1288666 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7190. Min Act: -0.0002

Data Index: 601524 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7196. Min Act: -0.0001

Data Index: 716138 (C4 (Web Text))

Max Activating Token Index: 95