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

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

Neuron 3801 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: 1.3963. Min Range: -1.3963

Max Act: 1.3963. Min Act: -0.0000

Data Index: 713963 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.2115. Min Act: -0.0000

Data Index: 942397 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1167124 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0859. Min Act: -0.0000

Data Index: 582551 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1260. Min Act: -0.0000

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1216. Min Act: -0.0000

Data Index: 976366 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1203977 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1018. Min Act: -0.0000

Data Index: 242555 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0930. Min Act: -0.0000

Data Index: 950032 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0884. Min Act: -0.0000

Data Index: 458262 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0746. Min Act: -0.0000

Data Index: 988816 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0889. Min Act: -0.0000

Data Index: 137716 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0800. Min Act: -0.0000

Data Index: 110292 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1257011 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0430. Min Act: -0.0000

Data Index: 786203 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9995. Min Act: -0.0000

Data Index: 345374 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9866. Min Act: -0.0000

Data Index: 370479 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9904. Min Act: -0.0000

Data Index: 97791 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0444. Min Act: -0.0000

Data Index: 441989 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0694. Min Act: -0.0000

Data Index: 980425 (C4 (Web Text))

Max Activating Token Index: 922