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

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

Neuron 3512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1302375 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0000

Data Index: 731412 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1026430 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1409040 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0635. Min Act: -0.0000

Data Index: 619194 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0593. Min Act: -0.0000

Data Index: 174200 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1305106 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0626. Min Act: -0.0000

Data Index: 976645 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0558. Min Act: -0.0000

Data Index: 458428 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0673. Min Act: -0.0000

Data Index: 441353 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0605. Min Act: -0.0000

Data Index: 719066 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1218767 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0556. Min Act: -0.0000

Data Index: 26466 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1243167 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0537. Min Act: -0.0000

Data Index: 348619 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0593. Min Act: -0.0000

Data Index: 900924 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0549. Min Act: -0.0000

Data Index: 835985 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1044933 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1075232 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0514. Min Act: -0.0000

Data Index: 593850 (C4 (Web Text))

Max Activating Token Index: 171