Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3374 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5544. Min Range: -3.5544

Max Act: 3.5544. Min Act: -0.0000

Data Index: 187138 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 3.5544. Min Range: -3.5544

Max Act: 3.5287. Min Act: -0.0000

Data Index: 1004662 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.5544. Min Range: -3.5544

Max Act: 3.3529. Min Act: -0.0000

Data Index: 734235 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.5544. Min Range: -3.5544

Max Act: 3.5064. Min Act: -0.0000

Data Index: 543020 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.9989. Min Act: -0.0000

Data Index: 1074002 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.7742. Min Act: -0.0000

Data Index: 317242 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.7668. Min Act: -0.0000

Data Index: 33540 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.7715. Min Act: -0.0000

Data Index: 570301 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.5770. Min Act: -0.0000

Data Index: 324231 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1583471 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.5129. Min Act: -0.0000

Data Index: 865087 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.5197. Min Act: -0.0000

Data Index: 1616226 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4723. Min Act: -0.0000

Data Index: 1368988 (Python Code)

Max Activating Token Index: 559

Text #13

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4447. Min Act: -0.0000

Data Index: 1364943 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.5492. Min Act: -0.0000

Data Index: 595294 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4173. Min Act: -0.0000

Data Index: 353483 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4101. Min Act: -0.0000

Data Index: 1578528 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1245009 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4113. Min Act: -0.0000

Data Index: 747533 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 3.5544. Min Range: -3.5544

Max Act: 2.4012. Min Act: -0.0000

Data Index: 1405420 (Python Code)

Max Activating Token Index: 127