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

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

Neuron 5511 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.8514. Min Act: -0.0000

Data Index: 188420 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.5759. Min Act: -0.0000

Data Index: 307646 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.3952. Min Act: -0.0000

Data Index: 1560546 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.3866. Min Act: -0.0000

Data Index: 1313328 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1118834 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.4436. Min Act: -0.0000

Data Index: 241712 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.2992. Min Act: -0.0000

Data Index: 986809 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.4014. Min Act: -0.0000

Data Index: 1341751 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.1953. Min Act: -0.0000

Data Index: 1279340 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.3206. Min Act: -0.0000

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0447. Min Act: -0.0000

Data Index: 862778 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0150. Min Act: -0.0000

Data Index: 765226 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.1382. Min Act: -0.0000

Data Index: 567427 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.1024. Min Act: -0.0000

Data Index: 287160 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0741. Min Act: -0.0000

Data Index: 269338 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0804. Min Act: -0.0000

Data Index: 324700 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1212133 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0714. Min Act: -0.0000

Data Index: 869188 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.0661. Min Act: -0.0000

Data Index: 154832 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.8514. Min Range: -2.8514

Max Act: 2.1551. Min Act: -0.0000

Data Index: 183988 (C4 (Web Text))

Max Activating Token Index: 618