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

Dataset: The Pile

Neuron 1920 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: 1.4711. Min Range: -1.4711

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1590888 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.4711. Min Act: -0.0000

Data Index: 1321909 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1085036 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.2463. Min Act: -0.0000

Data Index: 385794 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.2139. Min Act: -0.0000

Data Index: 476726 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1700521 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1018015 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.1057. Min Act: -0.0000

Data Index: 376326 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1550095 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.4711. Min Range: -1.4711

Max Act: 1.0170. Min Act: -0.0000

Data Index: 243627 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1871523 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1076969 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1667910 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1710262 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8838. Min Act: -0.0000

Data Index: 819385 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8941. Min Act: -0.0000

Data Index: 757559 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9439. Min Act: -0.0000

Data Index: 803804 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1232999 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1770451 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.4711. Min Range: -1.4711

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1285286 (The Pile)

Max Activating Token Index: 991