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

Dataset: The Pile

Neuron 2344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1017731 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.7689. Min Act: -0.0000

Data Index: 1669898 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.8196. Min Act: -0.0000

Data Index: 1697588 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.7125. Min Act: -0.0000

Data Index: 843866 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.6803. Min Act: -0.0000

Data Index: 756418 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.5611. Min Act: -0.0000

Data Index: 1883149 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4873. Min Act: -0.0000

Data Index: 949286 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1876367 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4639. Min Act: -0.0000

Data Index: 923681 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3658. Min Act: -0.0000

Data Index: 874405 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1490257 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1322697 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3979. Min Act: -0.0000

Data Index: 715254 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.5133. Min Act: -0.0000

Data Index: 295369 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4388. Min Act: -0.0000

Data Index: 758678 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1290912 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4484. Min Act: -0.0000

Data Index: 1182290 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3577. Min Act: -0.0000

Data Index: 149939 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1990012 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2764. Min Act: -0.0000

Data Index: 23268 (The Pile)

Max Activating Token Index: 63