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

Dataset: The Pile

Neuron 3126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4455. Min Range: -1.4455

Max Act: 1.4455. Min Act: -0.0000

Data Index: 163893 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 1.4455. Min Range: -1.4455

Max Act: 1.1584. Min Act: -0.0000

Data Index: 215442 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 1.4455. Min Range: -1.4455

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1353815 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 1.4455. Min Range: -1.4455

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1471477 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.9353. Min Act: -0.0000

Data Index: 35413 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1293830 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.8896. Min Act: -0.0000

Data Index: 924290 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1691911 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1138314 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1314075 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7818. Min Act: -0.0000

Data Index: 273463 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.8290. Min Act: -0.0000

Data Index: 595119 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1411737 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7770. Min Act: -0.0000

Data Index: 428980 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7646. Min Act: -0.0000

Data Index: 158113 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7928. Min Act: -0.0000

Data Index: 491484 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7540. Min Act: -0.0000

Data Index: 361786 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7400. Min Act: -0.0000

Data Index: 664221 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7480. Min Act: -0.0000

Data Index: 974727 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 1.4455. Min Range: -1.4455

Max Act: 0.7655. Min Act: -0.0000

Data Index: 42044 (The Pile)

Max Activating Token Index: 318