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

Dataset: The Pile

Neuron 3838 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: 1.1552. Min Range: -1.1552

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1395830 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.1522. Min Act: -0.0000

Data Index: 845138 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0630. Min Act: -0.0000

Data Index: 916670 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0952. Min Act: -0.0000

Data Index: 781844 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1961892 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1021146 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0444. Min Act: -0.0000

Data Index: 533560 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1816044 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1251968 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0535. Min Act: -0.0000

Data Index: 667362 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9817. Min Act: -0.0000

Data Index: 60467 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9652. Min Act: -0.0000

Data Index: 608766 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1844552 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1402984 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1254382 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8697. Min Act: -0.0000

Data Index: 178102 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1242330 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1403815 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9011. Min Act: -0.0000

Data Index: 135214 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1444271 (The Pile)

Max Activating Token Index: 785