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

Dataset: The Pile

Neuron 4884 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: 0.5415. Min Range: -0.5415

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1412155 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4992. Min Act: -0.0000

Data Index: 998358 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4476. Min Act: -0.0000

Data Index: 572898 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4399. Min Act: -0.0000

Data Index: 435401 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4403. Min Act: -0.0000

Data Index: 429348 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1108739 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1913367 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3939. Min Act: -0.0000

Data Index: 902391 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1707351 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1289044 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1746564 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3863. Min Act: -0.0000

Data Index: 352934 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4139. Min Act: -0.0000

Data Index: 854418 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4000. Min Act: -0.0000

Data Index: 884542 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3955. Min Act: -0.0000

Data Index: 319951 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1217147 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1859711 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1288828 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3781. Min Act: -0.0000

Data Index: 416548 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3825. Min Act: -0.0000

Data Index: 277114 (The Pile)

Max Activating Token Index: 752