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

Dataset: The Pile

Neuron 2547 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: 1.5880. Min Range: -1.5880

Max Act: 1.5880. Min Act: -0.0000

Data Index: 122005 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1822025 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3132. Min Act: -0.0000

Data Index: 325336 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2365. Min Act: -0.0000

Data Index: 111246 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2269. Min Act: -0.0000

Data Index: 922739 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1552647 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4019. Min Act: -0.0000

Data Index: 310887 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2192. Min Act: -0.0000

Data Index: 984736 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1787464 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2043. Min Act: -0.0000

Data Index: 158681 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1241740 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1250. Min Act: -0.0000

Data Index: 256583 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1140564 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1032. Min Act: -0.0000

Data Index: 53124 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1163. Min Act: -0.0000

Data Index: 153317 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1686516 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.0420. Min Act: -0.0000

Data Index: 553505 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1767790 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.0180. Min Act: -0.0000

Data Index: 973439 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1329751 (The Pile)

Max Activating Token Index: 212