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

Dataset: The Pile

Neuron 1012 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: 1.5424. Min Range: -1.5424

Max Act: 1.5424. Min Act: -0.0000

Data Index: 1252832 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1257530 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1232800 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1483473 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1903973 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1781. Min Act: -0.0000

Data Index: 585687 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1396. Min Act: -0.0000

Data Index: 33142 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1627071 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1064656 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1829326 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0470. Min Act: -0.0000

Data Index: 543859 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1451857 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1877927 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1176614 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0041. Min Act: -0.0000

Data Index: 729854 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1316884 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9473. Min Act: -0.0000

Data Index: 23970 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0895. Min Act: -0.0000

Data Index: 589690 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9708. Min Act: -0.0000

Data Index: 98486 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1937080 (The Pile)

Max Activating Token Index: 414