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

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

Neuron 5224 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: 0.3787. Min Range: -0.3787

Max Act: 0.3787. Min Act: -0.0000

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1199785 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1540855 (Python Code)

Max Activating Token Index: 392

Text #3

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3039. Min Act: -0.0000

Data Index: 71121 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2933. Min Act: -0.0000

Data Index: 875574 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1306181 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2758. Min Act: -0.0000

Data Index: 313349 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2510. Min Act: -0.0000

Data Index: 168921 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2744. Min Act: -0.0000

Data Index: 693867 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2687. Min Act: -0.0000

Data Index: 957176 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2794. Min Act: -0.0000

Data Index: 665081 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1590412 (Python Code)

Max Activating Token Index: 361

Text #12

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2350. Min Act: -0.0000

Data Index: 766247 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2572. Min Act: -0.0000

Data Index: 589160 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2578. Min Act: -0.0000

Data Index: 990121 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2571. Min Act: -0.0000

Data Index: 852353 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1328104 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2554. Min Act: -0.0000

Data Index: 187526 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1404643 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1642884 (Python Code)

Max Activating Token Index: 769