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

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

Neuron 3547 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1508833 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0605. Min Act: -0.0000

Data Index: 701656 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1594995 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0566. Min Act: -0.0000

Data Index: 871404 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1398469 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1239572 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1207711 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0523. Min Act: -0.0000

Data Index: 252288 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0501. Min Act: -0.0000

Data Index: 40629 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1533377 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1620851 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0523. Min Act: -0.0000

Data Index: 986134 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0520. Min Act: -0.0000

Data Index: 544162 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1541406 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0497. Min Act: -0.0000

Data Index: 536279 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1468067 (Python Code)

Max Activating Token Index: 408

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1231260 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1330782 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0490. Min Act: -0.0000

Data Index: 121777 (C4 (Web Text))

Max Activating Token Index: 486