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

Dataset: The Pile

Neuron 4096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1204140 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1241570 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9043. Min Act: -0.0000

Data Index: 17652 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8510. Min Act: -0.0000

Data Index: 737190 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1200466 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8542. Min Act: -0.0000

Data Index: 262393 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1284749 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1976921 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8522. Min Act: -0.0000

Data Index: 720980 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7972. Min Act: -0.0000

Data Index: 505432 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7426. Min Act: -0.0000

Data Index: 69685 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1804713 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1957724 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7997. Min Act: -0.0000

Data Index: 452063 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1693629 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1652882 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7170. Min Act: -0.0000

Data Index: 883153 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1266802 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1844096 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7658. Min Act: -0.0000

Data Index: 19814 (The Pile)

Max Activating Token Index: 728