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

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

Neuron 768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.5889. Min Act: -0.0000

Data Index: 1115538 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.7021. Min Act: -0.0000

Data Index: 1020455 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.8793. Min Act: -0.0000

Data Index: 352657 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.3739. Min Act: -0.0000

Data Index: 16469 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.3553. Min Act: -0.0000

Data Index: 1338934 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.0512. Min Act: -0.0000

Data Index: 151178 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.0739. Min Act: -0.0000

Data Index: 956401 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.2318. Min Act: -0.0000

Data Index: 26908 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.2318. Min Act: -0.0000

Data Index: 2027 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.2408. Min Act: -0.0000

Data Index: 584387 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.2125. Min Act: -0.0000

Data Index: 1269047 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.1724. Min Act: -0.0000

Data Index: 1030793 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 5.8793. Min Range: -5.8793

Max Act: 4.9343. Min Act: -0.0000

Data Index: 420890 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.1269. Min Act: -0.0000

Data Index: 897703 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.2442. Min Act: -0.0000

Data Index: 254914 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.0252. Min Act: -0.0000

Data Index: 1065638 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 5.8793. Min Range: -5.8793

Max Act: 4.8366. Min Act: -0.0000

Data Index: 388197 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 5.8793. Min Range: -5.8793

Max Act: 4.9741. Min Act: -0.0000

Data Index: 595152 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.8793. Min Range: -5.8793

Max Act: 4.7899. Min Act: -0.0000

Data Index: 299244 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 5.8793. Min Range: -5.8793

Max Act: 5.1331. Min Act: -0.0000

Data Index: 132368 (C4 (Web Text))

Max Activating Token Index: 43