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

Dataset: The Pile

Neuron 233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1801267 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8713. Min Act: -0.0000

Data Index: 975791 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1448576 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.7688. Min Act: -0.0000

Data Index: 455773 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.6147. Min Act: -0.0000

Data Index: 90219 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1878407 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5954. Min Act: -0.0000

Data Index: 547131 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1064709 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1883899 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1657298 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5563. Min Act: -0.0000

Data Index: 152652 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1467974 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5483. Min Act: -0.0000

Data Index: 507354 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1360275 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5559. Min Act: -0.0000

Data Index: 661602 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1525658 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1106511 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1700651 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1306909 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1304489 (The Pile)

Max Activating Token Index: 527