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

Dataset: The Pile

Neuron 3999 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.5990. Min Act: -0.0000

Data Index: 161278 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.6552. Min Act: -0.0000

Data Index: 994984 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.6703. Min Act: -0.0000

Data Index: 627319 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.4737. Min Act: 0.0000

Data Index: 1201716 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1826748 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3739. Min Act: -0.0000

Data Index: 722946 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3017. Min Act: -0.0000

Data Index: 427920 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1687882 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1125631 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1698472 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1553347 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3509. Min Act: -0.0000

Data Index: 1640615 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1430784 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.2825. Min Act: -0.0000

Data Index: 921725 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1607218 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1604394 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.2252. Min Act: -0.0000

Data Index: 554100 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1470044 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1726419 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.6703. Min Range: -1.6703

Max Act: 1.1491. Min Act: -0.0000

Data Index: 815525 (The Pile)

Max Activating Token Index: 303