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

Dataset: The Pile

Neuron 1968 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: 4.7719. Min Range: -4.7719

Max Act: 4.7719. Min Act: -0.0000

Data Index: 470967 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 4.7719. Min Range: -4.7719

Max Act: 4.2022. Min Act: -0.0000

Data Index: 600671 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.3515. Min Act: -0.0000

Data Index: 1261253 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.3893. Min Act: -0.0000

Data Index: 1588465 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1895. Min Act: -0.0000

Data Index: 1098033 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.6039. Min Act: -0.0000

Data Index: 1026302 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.8868. Min Act: -0.0000

Data Index: 334489 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1972. Min Act: -0.0000

Data Index: 12097 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1667. Min Act: -0.0000

Data Index: 1722482 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.3825. Min Act: -0.0000

Data Index: 368479 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.8442. Min Act: -0.0000

Data Index: 375147 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.9740. Min Act: -0.0000

Data Index: 454501 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.0455. Min Act: -0.0000

Data Index: 865639 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.9830. Min Act: -0.0000

Data Index: 429941 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.0763. Min Act: -0.0000

Data Index: 1232643 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.8820. Min Act: -0.0000

Data Index: 1875133 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 4.7719. Min Range: -4.7719

Max Act: 3.1684. Min Act: -0.0000

Data Index: 991420 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.7487. Min Act: -0.0000

Data Index: 1228383 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.8450. Min Act: -0.0000

Data Index: 887500 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 4.7719. Min Range: -4.7719

Max Act: 2.9441. Min Act: -0.0000

Data Index: 944605 (The Pile)

Max Activating Token Index: 958