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

Dataset: The Pile

Neuron 2808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6121. Min Range: -1.6121

Max Act: 1.6121. Min Act: -0.0000

Data Index: 285678 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.6121. Min Range: -1.6121

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1847224 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.8931. Min Act: -0.0000

Data Index: 406133 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6679. Min Act: -0.0000

Data Index: 871533 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1346615 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1584545 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1891756 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1437915 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.7979. Min Act: -0.0000

Data Index: 435492 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.9341. Min Act: -0.0000

Data Index: 193594 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1134162 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.7133. Min Act: -0.0000

Data Index: 311130 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.7014. Min Act: -0.0000

Data Index: 527958 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1204597 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1885234 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1532116 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1878602 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6624. Min Act: -0.0000

Data Index: 434330 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1344339 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 1.6121. Min Range: -1.6121

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1724337 (The Pile)

Max Activating Token Index: 790