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

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

Neuron 3920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0948. Min Act: -0.0000

Data Index: 642105 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9727. Min Act: -0.0000

Data Index: 240741 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9621. Min Act: -0.0000

Data Index: 513519 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8238. Min Act: -0.0000

Data Index: 904488 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8662. Min Act: -0.0000

Data Index: 97826 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7957. Min Act: -0.0000

Data Index: 643652 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7411. Min Act: -0.0000

Data Index: 749463 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6641. Min Act: -0.0000

Data Index: 780696 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6696. Min Act: -0.0000

Data Index: 118686 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6856. Min Act: -0.0000

Data Index: 659924 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7026. Min Act: -0.0000

Data Index: 829959 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1002282 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6611. Min Act: -0.0000

Data Index: 562995 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6984. Min Act: -0.0000

Data Index: 494555 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6647. Min Act: -0.0000

Data Index: 955335 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6612. Min Act: -0.0000

Data Index: 77906 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6618. Min Act: -0.0000

Data Index: 136864 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6612. Min Act: -0.0000

Data Index: 635582 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1046865 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6821. Min Act: -0.0000

Data Index: 694323 (C4 (Web Text))

Max Activating Token Index: 75