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

Dataset: The Pile

Neuron 1796 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: 0.3800. Min Range: -0.3800

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1178761 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1139736 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2998. Min Act: -0.0000

Data Index: 132813 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1168171 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1723297 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2913. Min Act: -0.0000

Data Index: 217572 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1879228 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1111461 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2685. Min Act: -0.0000

Data Index: 911340 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1251324 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2710. Min Act: -0.0000

Data Index: 687204 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1684269 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2717. Min Act: -0.0000

Data Index: 446155 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1639531 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2598. Min Act: -0.0000

Data Index: 963476 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1964227 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2589. Min Act: -0.0000

Data Index: 101796 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2394. Min Act: -0.0000

Data Index: 711809 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2657. Min Act: -0.0000

Data Index: 919992 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1938593 (The Pile)

Max Activating Token Index: 265