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

Dataset: The Pile

Neuron 2955 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1663. Min Range: -7.1663

Max Act: 7.1663. Min Act: -0.0000

Data Index: 1462194 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.9285. Min Act: -0.0000

Data Index: 168849 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 7.1663. Min Range: -7.1663

Max Act: 7.0059. Min Act: -0.0000

Data Index: 1650430 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.7274. Min Act: -0.0000

Data Index: 168893 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.5570. Min Act: 0.0000

Data Index: 1558486 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.6737. Min Act: -0.0000

Data Index: 1687138 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.9145. Min Act: -0.0000

Data Index: 326543 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.1678. Min Act: 0.0000

Data Index: 1060156 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.2336. Min Act: -0.0000

Data Index: 513588 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.3204. Min Act: -0.0000

Data Index: 40220 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 7.1663. Min Range: -7.1663

Max Act: 6.2903. Min Act: -0.0000

Data Index: 728395 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.5347. Min Act: -0.0000

Data Index: 1252774 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 7.1663. Min Range: -7.1663

Max Act: 4.9045. Min Act: -0.0000

Data Index: 150580 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.9370. Min Act: -0.0000

Data Index: 1602289 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.8814. Min Act: -0.0000

Data Index: 19060 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.2436. Min Act: -0.0000

Data Index: 1959576 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.8731. Min Act: -0.0000

Data Index: 371165 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.6614. Min Act: -0.0000

Data Index: 646371 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.8858. Min Act: -0.0000

Data Index: 128132 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 7.1663. Min Range: -7.1663

Max Act: 5.6270. Min Act: -0.0000

Data Index: 184828 (The Pile)

Max Activating Token Index: 655