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

Dataset: The Pile

Neuron 2698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.4660. Min Act: -0.0000

Data Index: 824884 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.6178. Min Act: -0.0000

Data Index: 1766937 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.3475. Min Act: -0.0000

Data Index: 1522405 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0300. Min Act: -0.0000

Data Index: 897127 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1652. Min Act: -0.0000

Data Index: 545638 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1418. Min Act: -0.0000

Data Index: 1652520 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1423. Min Act: -0.0000

Data Index: 357595 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1364. Min Act: -0.0000

Data Index: 468909 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9921. Min Act: -0.0000

Data Index: 684704 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1183. Min Act: -0.0000

Data Index: 1643099 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.8413. Min Act: -0.0000

Data Index: 1939273 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9047. Min Act: -0.0000

Data Index: 99141 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.8937. Min Act: -0.0000

Data Index: 624563 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0034. Min Act: -0.0000

Data Index: 1769278 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9746. Min Act: -0.0000

Data Index: 527867 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9562. Min Act: -0.0000

Data Index: 170736 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9519. Min Act: -0.0000

Data Index: 1434252 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9142. Min Act: -0.0000

Data Index: 181339 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0698. Min Act: -0.0000

Data Index: 998155 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9056. Min Act: -0.0000

Data Index: 1402199 (The Pile)

Max Activating Token Index: 324