Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1489 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0005

Data Index: 1434890 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1578370 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0251. Min Act: -0.0005

Data Index: 1412550 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1629319 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1474599 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0005

Data Index: 1581751 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1506573 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1554739 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1649076 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1633043 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1474792 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1398120 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0241. Min Act: -0.0005

Data Index: 606867 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0241. Min Act: -0.0005

Data Index: 1424420 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1389755 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1376993 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1556001 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1563579 (Python Code)

Max Activating Token Index: 749

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1572132 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1612918 (Python Code)

Max Activating Token Index: 698