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

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

Neuron 3194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1529436 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1527533 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1577818 (Python Code)

Max Activating Token Index: 767

Text #3

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1459184 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1480590 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6820. Min Act: -0.0001

Data Index: 1389786 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1563101 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1612470 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1503910 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1564967 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1632843 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1439864 (Python Code)

Max Activating Token Index: 486

Text #12

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1367688 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1425174 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1624554 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1655854 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1641292 (Python Code)

Max Activating Token Index: 748

Text #17

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1556362 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1385846 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1402952 (Python Code)

Max Activating Token Index: 814