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

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

Neuron 516 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: 0.7703. Min Range: -0.7703

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1510706 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1547794 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1482625 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1534966 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1632355 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1556970 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1388081 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1453589 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1576430 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1601972 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1493768 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1455414 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1493957 (Python Code)

Max Activating Token Index: 270

Text #13

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1372771 (Python Code)

Max Activating Token Index: 253

Text #14

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1373200 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1433976 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1551200 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1391236 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1648083 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1652529 (Python Code)

Max Activating Token Index: 296