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

Dataset: The Pile

Neuron 2344 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: 1.5900. Min Range: -1.5900

Max Act: 1.3073. Min Act: -0.0000

Data Index: 368588 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1503637 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.5900. Min Act: -0.0001

Data Index: 334257 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.4069. Min Act: -0.0000

Data Index: 490515 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1856619 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.2442. Min Act: -0.0000

Data Index: 858711 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.8428. Min Act: -0.0000

Data Index: 891181 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1604. Min Act: -0.0000

Data Index: 294132 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1004247 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.0974. Min Act: -0.0000

Data Index: 665644 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.0973. Min Act: -0.0000

Data Index: 732157 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1017056 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.8282. Min Act: -0.0000

Data Index: 292216 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1960804 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1047478 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.0917. Min Act: -0.0000

Data Index: 993257 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9427. Min Act: -0.0000

Data Index: 310637 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1130905 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1567353 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9544. Min Act: -0.0000

Data Index: 140651 (The Pile)

Max Activating Token Index: 619