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

Dataset: The Pile

Neuron 1800 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: 1.8684. Min Range: -1.8684

Max Act: 1.8684. Min Act: -0.0000

Data Index: 230250 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1500011 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1228658 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1873924 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3069. Min Act: -0.0000

Data Index: 366788 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3578. Min Act: -0.0000

Data Index: 296854 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1021245 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2379. Min Act: -0.0000

Data Index: 273831 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1320442 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 1.8684. Min Range: -1.8684

Max Act: 0.9972. Min Act: -0.0000

Data Index: 390306 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2073. Min Act: -0.0000

Data Index: 488384 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1116821 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1454691 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2553. Min Act: -0.0000

Data Index: 275587 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1897792 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1156532 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2676. Min Act: -0.0000

Data Index: 163338 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1843148 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1270781 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1407043 (The Pile)

Max Activating Token Index: 971