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

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

Neuron 2121 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4427. Min Range: -2.4427

Max Act: 2.4427. Min Act: -0.0000

Data Index: 1084377 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.9610. Min Act: -0.0000

Data Index: 1279272 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.9449. Min Act: -0.0000

Data Index: 425333 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 2.4427. Min Range: -2.4427

Max Act: 2.0975. Min Act: -0.0000

Data Index: 1188174 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.8094. Min Act: -0.0000

Data Index: 622695 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1135199 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.6631. Min Act: -0.0000

Data Index: 30674 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5370. Min Act: -0.0000

Data Index: 841881 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1082831 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5412. Min Act: -0.0000

Data Index: 59076 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1087623 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5845. Min Act: -0.0000

Data Index: 370665 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5140. Min Act: -0.0000

Data Index: 899272 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1054967 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.4625. Min Act: -0.0000

Data Index: 239939 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.4836. Min Act: -0.0000

Data Index: 965077 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.5643. Min Act: -0.0000

Data Index: 677975 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1222659 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.3943. Min Act: -0.0000

Data Index: 913949 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.4427. Min Range: -2.4427

Max Act: 1.4325. Min Act: -0.0000

Data Index: 462992 (C4 (Web Text))

Max Activating Token Index: 927