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

Dataset: The Pile

Neuron 4681 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: 0.9338. Min Range: -0.9338

Max Act: 0.9338. Min Act: -0.0000

Data Index: 491001 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1426517 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1052899 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7925. Min Act: -0.0000

Data Index: 138864 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7862. Min Act: -0.0000

Data Index: 567318 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1383278 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1936072 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7543. Min Act: -0.0000

Data Index: 51783 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1540512 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7285. Min Act: -0.0000

Data Index: 365481 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7506. Min Act: -0.0000

Data Index: 669380 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7277. Min Act: -0.0000

Data Index: 216404 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7210. Min Act: -0.0000

Data Index: 269755 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1229408 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6855. Min Act: -0.0000

Data Index: 806263 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1923354 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1771551 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1982842 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1814936 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6223. Min Act: -0.0000

Data Index: 538611 (The Pile)

Max Activating Token Index: 131