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

Dataset: The Pile

Neuron 3871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1971036 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7771. Min Act: -0.0000

Data Index: 531307 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1700073 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6705. Min Act: -0.0000

Data Index: 360195 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1232291 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6767. Min Act: -0.0000

Data Index: 997658 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1184745 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6976. Min Act: -0.0000

Data Index: 81237 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1428883 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7206. Min Act: -0.0000

Data Index: 713629 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6773. Min Act: -0.0000

Data Index: 679071 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6559. Min Act: -0.0000

Data Index: 801045 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6557. Min Act: -0.0000

Data Index: 617721 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6600. Min Act: -0.0000

Data Index: 981338 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1936654 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6396. Min Act: -0.0000

Data Index: 830432 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1652051 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1791018 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1336837 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6890. Min Act: -0.0000

Data Index: 395302 (The Pile)

Max Activating Token Index: 1021