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

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

Neuron 3288 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0001

Data Index: 17082 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1180272 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0836. Min Act: -0.0001

Data Index: 947523 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0818. Min Act: -0.0001

Data Index: 913046 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0803. Min Act: -0.0001

Data Index: 24819 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0806. Min Act: -0.0001

Data Index: 310071 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1198785 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0795. Min Act: -0.0001

Data Index: 427824 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0790. Min Act: -0.0001

Data Index: 610196 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0805. Min Act: -0.0001

Data Index: 285188 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1257446 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0786. Min Act: -0.0001

Data Index: 90724 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0793. Min Act: -0.0001

Data Index: 845207 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1196533 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0784. Min Act: -0.0001

Data Index: 168564 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0786. Min Act: -0.0001

Data Index: 591598 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0791. Min Act: -0.0001

Data Index: 27137 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1346841 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1182883 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0788. Min Act: -0.0001

Data Index: 557243 (C4 (Web Text))

Max Activating Token Index: 31