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

Dataset: The Pile

Neuron 3031 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6575. Min Act: -0.0000

Data Index: 518592 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1787154 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1523411 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1915068 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5416. Min Act: 0.0000

Data Index: 1370809 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1140367 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1635925 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5006. Min Act: -0.0000

Data Index: 434831 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1098384 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3899. Min Act: -0.0000

Data Index: 901621 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4600. Min Act: -0.0000

Data Index: 869977 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4222. Min Act: -0.0000

Data Index: 191485 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1104594 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1791095 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1071996 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4297. Min Act: -0.0000

Data Index: 331659 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4047. Min Act: 0.0000

Data Index: 684151 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1525620 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1487849 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4003. Min Act: -0.0000

Data Index: 760676 (The Pile)

Max Activating Token Index: 837