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

Dataset: The Pile

Neuron 3100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9835. Min Act: -0.0000

Data Index: 125928 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1866254 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9241. Min Act: -0.0000

Data Index: 481987 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8120. Min Act: -0.0000

Data Index: 522780 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8818. Min Act: -0.0000

Data Index: 110839 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8365. Min Act: -0.0000

Data Index: 218362 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1657183 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1570857 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1644478 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1075206 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7412. Min Act: -0.0000

Data Index: 610003 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1804499 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1514638 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7836. Min Act: -0.0000

Data Index: 487452 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6957. Min Act: -0.0000

Data Index: 85341 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7664. Min Act: -0.0000

Data Index: 961670 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7353. Min Act: -0.0000

Data Index: 773038 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6509. Min Act: -0.0000

Data Index: 107195 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6422. Min Act: -0.0000

Data Index: 266047 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1713621 (The Pile)

Max Activating Token Index: 485