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

Dataset: The Pile

Neuron 2780 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: 0.6675. Min Range: -0.6675

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1626278 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6510. Min Act: -0.0000

Data Index: 696772 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6668. Min Act: -0.0000

Data Index: 516160 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1436050 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6315. Min Act: -0.0000

Data Index: 946153 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5482. Min Act: -0.0000

Data Index: 799456 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1370713 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5937. Min Act: -0.0000

Data Index: 80792 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5813. Min Act: -0.0000

Data Index: 65065 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5624. Min Act: 0.0000

Data Index: 1946517 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5452. Min Act: 0.0000

Data Index: 978773 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5377. Min Act: -0.0000

Data Index: 663657 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5182. Min Act: -0.0000

Data Index: 530584 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5488. Min Act: -0.0000

Data Index: 92369 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1721051 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5266. Min Act: 0.0000

Data Index: 100274 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5369. Min Act: 0.0000

Data Index: 804707 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5311. Min Act: 0.0000

Data Index: 1368430 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1575856 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1438556 (The Pile)

Max Activating Token Index: 577