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

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

Neuron 2816 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: 3.7939. Min Range: -3.7939

Max Act: 3.7939. Min Act: -0.0000

Data Index: 1393695 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 3.7939. Min Range: -3.7939

Max Act: 3.2920. Min Act: -0.0000

Data Index: 1437406 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 3.7939. Min Range: -3.7939

Max Act: 3.1142. Min Act: -0.0000

Data Index: 1505368 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 3.7939. Min Range: -3.7939

Max Act: 3.0935. Min Act: -0.0000

Data Index: 1577833 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 3.7939. Min Range: -3.7939

Max Act: 3.0770. Min Act: -0.0000

Data Index: 1522677 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.7879. Min Act: -0.0000

Data Index: 1431398 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8902. Min Act: -0.0000

Data Index: 1616666 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 3.7939. Min Range: -3.7939

Max Act: 3.2050. Min Act: -0.0000

Data Index: 1629003 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.9549. Min Act: -0.0000

Data Index: 1476540 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.9436. Min Act: -0.0000

Data Index: 1456876 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.7912. Min Act: -0.0000

Data Index: 1625663 (Python Code)

Max Activating Token Index: 754

Text #11

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.9351. Min Act: -0.0000

Data Index: 1382632 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8026. Min Act: -0.0000

Data Index: 1577766 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.9090. Min Act: -0.0000

Data Index: 1655285 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.9215. Min Act: -0.0000

Data Index: 1499312 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8939. Min Act: -0.0000

Data Index: 1516291 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8865. Min Act: -0.0000

Data Index: 1620046 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.6998. Min Act: -0.0000

Data Index: 1645307 (Python Code)

Max Activating Token Index: 557

Text #18

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8359. Min Act: -0.0000

Data Index: 1489436 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 3.7939. Min Range: -3.7939

Max Act: 2.8108. Min Act: -0.0000

Data Index: 1572161 (Python Code)

Max Activating Token Index: 356