Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4773 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.2978. Min Act: 0.0000

Data Index: 892127 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0757. Min Act: -0.0000

Data Index: 50245 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9436. Min Act: -0.0000

Data Index: 219586 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9540. Min Act: -0.0000

Data Index: 745005 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8349. Min Act: -0.0000

Data Index: 431728 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1316827 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7983. Min Act: -0.0000

Data Index: 666914 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7293. Min Act: -0.0000

Data Index: 349047 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1100118 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7680. Min Act: -0.0000

Data Index: 674551 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.6995. Min Act: -0.0000

Data Index: 894093 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7416. Min Act: -0.0000

Data Index: 107868 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7254. Min Act: -0.0000

Data Index: 752204 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7181. Min Act: -0.0000

Data Index: 64009 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7142. Min Act: -0.0000

Data Index: 157833 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7080. Min Act: -0.0000

Data Index: 186171 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.6938. Min Act: -0.0000

Data Index: 449191 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.6721. Min Act: -0.0000

Data Index: 13385 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1063446 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.6337. Min Act: -0.0000

Data Index: 503710 (C4 (Web Text))

Max Activating Token Index: 23