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

Dataset: The Pile

Neuron 2907 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: 0.7591. Min Range: -0.7591

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1053035 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7344. Min Act: -0.0000

Data Index: 785731 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7078. Min Act: -0.0000

Data Index: 586333 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7140. Min Act: -0.0000

Data Index: 214516 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7276. Min Act: -0.0000

Data Index: 892524 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1586678 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1568832 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6623. Min Act: -0.0000

Data Index: 956184 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6528. Min Act: -0.0000

Data Index: 795053 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1357293 (The Pile)

Max Activating Token Index: 782

Text #10

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1845121 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1432614 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1353496 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1803737 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6217. Min Act: -0.0000

Data Index: 742403 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1021230 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6610. Min Act: -0.0000

Data Index: 141263 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1030270 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1263487 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1240257 (The Pile)

Max Activating Token Index: 521