Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 404 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0000

Data Index: 531832 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1231. Min Act: -0.0000

Data Index: 194727 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1333397 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1783315 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0983. Min Act: -0.0000

Data Index: 610614 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1066. Min Act: -0.0000

Data Index: 236350 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1164686 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1014977 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0942. Min Act: -0.0001

Data Index: 470432 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0980. Min Act: -0.0001

Data Index: 552892 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1287665 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0868. Min Act: -0.0000

Data Index: 493751 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0906. Min Act: -0.0000

Data Index: 165713 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0899. Min Act: -0.0000

Data Index: 75851 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0900. Min Act: -0.0000

Data Index: 457537 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0858. Min Act: -0.0000

Data Index: 191788 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1785346 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0884. Min Act: -0.0000

Data Index: 454325 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1613141 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.0857. Min Act: -0.0001

Data Index: 895328 (The Pile)

Max Activating Token Index: 547