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

Dataset: The Pile

Neuron 565 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: 1.6675. Min Range: -1.6675

Max Act: 1.6675. Min Act: -0.0000

Data Index: 1305634 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3494. Min Act: -0.0000

Data Index: 767776 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.0274. Min Act: -0.0000

Data Index: 305616 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1818264 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.0970. Min Act: -0.0000

Data Index: 434816 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.0294. Min Act: -0.0000

Data Index: 781481 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1209362 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9445. Min Act: -0.0000

Data Index: 699517 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1084370 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9281. Min Act: -0.0000

Data Index: 634728 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1378258 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1286583 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1159019 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1257822 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8303. Min Act: -0.0000

Data Index: 673668 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8864. Min Act: -0.0000

Data Index: 828545 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.9177. Min Act: -0.0000

Data Index: 262620 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8384. Min Act: -0.0000

Data Index: 675561 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1093454 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 1.6675. Min Range: -1.6675

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1472893 (The Pile)

Max Activating Token Index: 423