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

Dataset: The Pile

Neuron 2265 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: 0.6471. Min Range: -0.6471

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1445741 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6255. Min Act: -0.0000

Data Index: 500752 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1331450 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5872. Min Act: -0.0000

Data Index: 316211 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5561. Min Act: -0.0000

Data Index: 848813 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1884544 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5442. Min Act: -0.0000

Data Index: 332729 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1147824 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5036. Min Act: -0.0000

Data Index: 914941 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1887901 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4580. Min Act: -0.0000

Data Index: 36058 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1280229 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4550. Min Act: -0.0000

Data Index: 33495 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1381713 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4613. Min Act: -0.0000

Data Index: 80683 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4278. Min Act: -0.0000

Data Index: 337911 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1807175 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.3881. Min Act: -0.0000

Data Index: 403579 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1517286 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1047038 (The Pile)

Max Activating Token Index: 912