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

Dataset: The Pile

Neuron 3057 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.3109. Min Act: -0.0000

Data Index: 75757 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1660331 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.2530. Min Act: -0.0000

Data Index: 49404 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1923621 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1025518 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1030967 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 1.3109. Min Range: -1.3109

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1824336 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1823250 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1296585 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.1752. Min Act: -0.0000

Data Index: 315473 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1136905 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.3109. Min Range: -1.3109

Max Act: 0.9998. Min Act: -0.0000

Data Index: 263451 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1747421 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.1048. Min Act: -0.0000

Data Index: 228678 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1367688 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.3109. Min Range: -1.3109

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1380637 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0447. Min Act: -0.0000

Data Index: 551029 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.3109. Min Range: -1.3109

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1214337 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 1.3109. Min Range: -1.3109

Max Act: 0.9566. Min Act: -0.0000

Data Index: 62692 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 1.3109. Min Range: -1.3109

Max Act: 1.0849. Min Act: -0.0000

Data Index: 417114 (The Pile)

Max Activating Token Index: 465