Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0001

Data Index: 745813 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1208212 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0556. Min Act: -0.0000

Data Index: 453727 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1022837 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1524367 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1577808 (Python Code)

Max Activating Token Index: 451

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1434456 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0494. Min Act: -0.0001

Data Index: 271679 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0484. Min Act: -0.0000

Data Index: 598148 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0480. Min Act: -0.0000

Data Index: 105496 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1341370 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1613029 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1287121 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1521749 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0472. Min Act: -0.0001

Data Index: 563881 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0457. Min Act: -0.0000

Data Index: 966425 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1403212 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0482. Min Act: -0.0000

Data Index: 706897 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0428. Min Act: -0.0000

Data Index: 832095 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0454. Min Act: -0.0000

Data Index: 942559 (C4 (Web Text))

Max Activating Token Index: 805