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

Dataset: The Pile

Neuron 284 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: -0.0000

Data Index: 106614 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1356331 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1625484 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6861. Min Act: -0.0000

Data Index: 191593 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1938393 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1077800 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6342. Min Act: -0.0000

Data Index: 777409 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1159546 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1732786 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1183723 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5440. Min Act: -0.0000

Data Index: 224092 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1257126 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1009658 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5737. Min Act: -0.0000

Data Index: 429393 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1028953 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1428321 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1630860 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1206526 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5220. Min Act: -0.0000

Data Index: 170323 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1707664 (The Pile)

Max Activating Token Index: 380