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

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

Neuron 453 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6954. Min Range: -2.6954

Max Act: 2.6954. Min Act: -0.0000

Data Index: 81266 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.6954. Min Range: -2.6954

Max Act: 2.0500. Min Act: -0.0000

Data Index: 535278 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 2.6954. Min Range: -2.6954

Max Act: 2.0664. Min Act: -0.0000

Data Index: 538269 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.7710. Min Act: -0.0000

Data Index: 175022 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.7689. Min Act: -0.0000

Data Index: 394969 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.7082. Min Act: -0.0000

Data Index: 627096 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1190028 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6723. Min Act: -0.0000

Data Index: 870636 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.5676. Min Act: -0.0000

Data Index: 719632 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6664. Min Act: -0.0000

Data Index: 125708 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6444. Min Act: -0.0000

Data Index: 88946 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.4802. Min Act: -0.0000

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1023480 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6525. Min Act: -0.0000

Data Index: 239845 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6220. Min Act: -0.0000

Data Index: 609313 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6263. Min Act: -0.0000

Data Index: 116874 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6260. Min Act: -0.0000

Data Index: 223175 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.6242. Min Act: -0.0000

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.6954. Min Range: -2.6954

Max Act: 1.5915. Min Act: -0.0000

Data Index: 994131 (C4 (Web Text))

Max Activating Token Index: 78