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

Dataset: The Pile

Neuron 3860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.3900. Min Act: -0.0000

Data Index: 662480 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.2600. Min Act: -0.0000

Data Index: 692056 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0588. Min Act: -0.0000

Data Index: 893801 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1161845 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0315. Min Act: -0.0000

Data Index: 141960 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0785. Min Act: -0.0000

Data Index: 424312 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9279. Min Act: -0.0000

Data Index: 783495 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9307. Min Act: -0.0000

Data Index: 250370 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1743177 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1810228 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1322233 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1492438 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1927459 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8662. Min Act: -0.0000

Data Index: 991826 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1671684 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8586. Min Act: -0.0000

Data Index: 531898 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1723027 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1418565 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1141234 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1306767 (The Pile)

Max Activating Token Index: 473