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

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

Neuron 1049 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: 1.0064. Min Range: -1.0064

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1317870 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8870. Min Act: -0.0000

Data Index: 176688 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9158. Min Act: -0.0000

Data Index: 266212 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8994. Min Act: -0.0000

Data Index: 277700 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9279. Min Act: -0.0000

Data Index: 412800 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1089457 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1216062 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9112. Min Act: -0.0000

Data Index: 197771 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8500. Min Act: -0.0000

Data Index: 641805 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8501. Min Act: -0.0000

Data Index: 305497 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8003. Min Act: -0.0000

Data Index: 365066 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7848. Min Act: -0.0000

Data Index: 445166 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8117. Min Act: -0.0000

Data Index: 596377 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7605. Min Act: -0.0000

Data Index: 276059 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1329199 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7614. Min Act: -0.0000

Data Index: 54695 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1145832 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1168910 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7298. Min Act: -0.0000

Data Index: 649657 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1153178 (C4 (Web Text))

Max Activating Token Index: 114