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

Dataset: The Pile

Neuron 821 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: 0.5696. Min Range: -0.5696

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1720245 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0000

Data Index: 226270 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5479. Min Act: -0.0000

Data Index: 24269 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4988. Min Act: -0.0000

Data Index: 787258 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1852254 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1218543 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1188178 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4140. Min Act: -0.0000

Data Index: 13741 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4772. Min Act: -0.0000

Data Index: 331540 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4492. Min Act: -0.0000

Data Index: 236505 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4453. Min Act: -0.0000

Data Index: 470084 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1564163 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4209. Min Act: -0.0000

Data Index: 68513 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1017302 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4157. Min Act: -0.0000

Data Index: 274333 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1820344 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4198. Min Act: -0.0000

Data Index: 157375 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4036. Min Act: -0.0000

Data Index: 64881 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1000756 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3628. Min Act: -0.0000

Data Index: 203493 (The Pile)

Max Activating Token Index: 544