Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1438195 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1409964 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1621713 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 1.0169. Min Range: -1.0169

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1576308 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1586504 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7239. Min Act: -0.0001

Data Index: 1375850 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1574139 (Python Code)

Max Activating Token Index: 521

Text #7

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6729. Min Act: -0.0001

Data Index: 1435998 (Python Code)

Max Activating Token Index: 469

Text #8

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1371963 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1636890 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6925. Min Act: -0.0001

Data Index: 1646673 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6593. Min Act: -0.0001

Data Index: 1504956 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6663. Min Act: -0.0001

Data Index: 1457045 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1474209 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6503. Min Act: -0.0001

Data Index: 1511925 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1376755 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1582013 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1391426 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6342. Min Act: -0.0001

Data Index: 1547852 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1390622 (Python Code)

Max Activating Token Index: 317