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

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

Neuron 5378 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: 3.2370. Min Range: -3.2370

Max Act: 3.2370. Min Act: -0.0000

Data Index: 1583972 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.5899. Min Act: -0.0000

Data Index: 1364750 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.5038. Min Act: -0.0000

Data Index: 1380139 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.4840. Min Act: -0.0000

Data Index: 1403271 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1371387 (Python Code)

Max Activating Token Index: 723

Text #5

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.4461. Min Act: -0.0000

Data Index: 1570909 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.2712. Min Act: -0.0000

Data Index: 1567481 (Python Code)

Max Activating Token Index: 913

Text #7

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1368421 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.1868. Min Act: -0.0000

Data Index: 1551207 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.2125. Min Act: -0.0000

Data Index: 1627218 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.2315. Min Act: -0.0000

Data Index: 1610393 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1551754 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.0560. Min Act: -0.0000

Data Index: 1467697 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.0252. Min Act: -0.0000

Data Index: 1656682 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1534963 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.1178. Min Act: -0.0000

Data Index: 1624752 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1408903 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.0085. Min Act: -0.0000

Data Index: 1528458 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.0796. Min Act: -0.0000

Data Index: 1504818 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 3.2370. Min Range: -3.2370

Max Act: 2.0556. Min Act: -0.0000

Data Index: 1397526 (Python Code)

Max Activating Token Index: 117