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

Dataset: The Pile

Neuron 3682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.2572. Min Act: -0.0000

Data Index: 141087 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.1275. Min Act: -0.0000

Data Index: 47693 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.1832. Min Act: -0.0000

Data Index: 5398 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1999236 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0798. Min Act: -0.0000

Data Index: 1254678 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1169915 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1653069 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1915459 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9347. Min Act: -0.0000

Data Index: 743480 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9973. Min Act: -0.0000

Data Index: 243422 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0547. Min Act: -0.0000

Data Index: 529479 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9793. Min Act: -0.0000

Data Index: 535260 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1978691 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9287. Min Act: -0.0000

Data Index: 755632 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1700723 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1655833 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1690217 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9694. Min Act: -0.0000

Data Index: 729579 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1250416 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9693. Min Act: -0.0000

Data Index: 721269 (The Pile)

Max Activating Token Index: 540