Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1390694 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1548574 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1440997 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1595247 (Python Code)

Max Activating Token Index: 1017

Text #4

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1604843 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1476054 (Python Code)

Max Activating Token Index: 137

Text #6

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1365422 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1601973 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1414589 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1505902 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1652937 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1411243 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1467528 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.3125. Min Act: 0.0000

Data Index: 1517181 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2229. Min Act: 0.0000

Data Index: 1421061 (Python Code)

Max Activating Token Index: 193

Text #15

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1491756 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1583087 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1455874 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1387428 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 1.4649. Min Range: -1.4649

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1466048 (Python Code)

Max Activating Token Index: 133