Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0643. Min Act: -0.0000

Data Index: 1662779 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4989. Min Act: -0.0000

Data Index: 23348 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4814. Min Act: -0.0000

Data Index: 392394 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4743. Min Act: -0.0000

Data Index: 1416278 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.3646. Min Act: -0.0000

Data Index: 1617599 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1584. Min Act: -0.0000

Data Index: 1891659 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1555. Min Act: -0.0000

Data Index: 659442 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.2645. Min Act: -0.0000

Data Index: 1606426 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1167. Min Act: -0.0000

Data Index: 41136 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.2366. Min Act: -0.0000

Data Index: 1905054 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1701349 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.9678. Min Act: -0.0000

Data Index: 906115 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1093. Min Act: -0.0000

Data Index: 1216233 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.2270. Min Act: -0.0000

Data Index: 415519 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1003. Min Act: -0.0000

Data Index: 557330 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.2322. Min Act: -0.0000

Data Index: 1968433 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.8703. Min Act: -0.0000

Data Index: 1343382 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.0057. Min Act: -0.0000

Data Index: 1526278 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1537. Min Act: -0.0000

Data Index: 30929 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.9986. Min Act: -0.0000

Data Index: 581677 (The Pile)

Max Activating Token Index: 400