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

Dataset: The Pile

Neuron 3882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1191587 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1793289 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1699497 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5369. Min Act: -0.0000

Data Index: 315833 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1704201 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1513758 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5095. Min Act: -0.0000

Data Index: 264030 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4972. Min Act: -0.0000

Data Index: 6787 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4822. Min Act: -0.0000

Data Index: 981883 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1090249 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4361. Min Act: -0.0000

Data Index: 513061 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1316280 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4562. Min Act: 0.0001

Data Index: 1880118 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4447. Min Act: -0.0000

Data Index: 488359 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1290848 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4372. Min Act: 0.0000

Data Index: 1222610 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1918913 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4218. Min Act: -0.0000

Data Index: 383307 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.3943. Min Act: -0.0000

Data Index: 367167 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1926385 (The Pile)

Max Activating Token Index: 455