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

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

Neuron 327 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: 0.0629. Min Range: -0.0629

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1159109 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0587. Min Act: -0.0000

Data Index: 504177 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1094002 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0592. Min Act: -0.0000

Data Index: 450127 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1056127 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0568. Min Act: -0.0000

Data Index: 124742 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0540. Min Act: -0.0000

Data Index: 298794 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1135333 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0571. Min Act: -0.0000

Data Index: 271855 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1441625 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1612984 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0514. Min Act: -0.0000

Data Index: 444831 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0539. Min Act: -0.0000

Data Index: 842469 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0513. Min Act: -0.0000

Data Index: 996571 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0540. Min Act: -0.0000

Data Index: 587354 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0507. Min Act: -0.0000

Data Index: 959025 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1163697 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0483. Min Act: -0.0000

Data Index: 78876 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0501. Min Act: -0.0000

Data Index: 425407 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0506. Min Act: -0.0000

Data Index: 71319 (C4 (Web Text))

Max Activating Token Index: 921