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

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

Neuron 2309 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 403451 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4114. Min Act: -0.0000

Data Index: 984977 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3893. Min Act: -0.0000

Data Index: 367351 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3782. Min Act: -0.0000

Data Index: 793861 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3953. Min Act: -0.0000

Data Index: 853695 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3911. Min Act: -0.0000

Data Index: 457989 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1090843 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3748. Min Act: -0.0000

Data Index: 928589 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3892. Min Act: -0.0000

Data Index: 648496 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4005. Min Act: -0.0000

Data Index: 368082 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1236895 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3570. Min Act: -0.0000

Data Index: 402585 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3401. Min Act: -0.0000

Data Index: 8085 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1021769 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1105197 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3491. Min Act: -0.0000

Data Index: 461099 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1581901 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1087092 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3565. Min Act: -0.0000

Data Index: 375773 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3536. Min Act: -0.0000

Data Index: 363739 (C4 (Web Text))

Max Activating Token Index: 40