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

Dataset: The Pile

Neuron 3885 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: 0.8232. Min Range: -0.8232

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1831351 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7692. Min Act: -0.0000

Data Index: 422858 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7372. Min Act: -0.0000

Data Index: 139164 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7521. Min Act: -0.0000

Data Index: 48017 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1022175 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1696280 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7490. Min Act: -0.0000

Data Index: 374525 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1336133 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6450. Min Act: -0.0000

Data Index: 981231 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1698527 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1291395 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7007. Min Act: -0.0000

Data Index: 475503 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1217023 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7349. Min Act: -0.0000

Data Index: 954230 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1991243 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6577. Min Act: -0.0000

Data Index: 570217 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1071836 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5909. Min Act: -0.0000

Data Index: 373635 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1592122 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6446. Min Act: -0.0000

Data Index: 564987 (The Pile)

Max Activating Token Index: 1020