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

Dataset: The Pile

Neuron 3384 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: 0.5856. Min Range: -0.5856

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1481630 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1888137 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1564245 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1819543 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5099. Min Act: -0.0000

Data Index: 383470 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4688. Min Act: -0.0000

Data Index: 339357 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1159462 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4774. Min Act: -0.0000

Data Index: 340417 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5183. Min Act: -0.0000

Data Index: 549957 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1583559 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1434723 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4732. Min Act: -0.0000

Data Index: 450914 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4479. Min Act: -0.0000

Data Index: 418039 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4436. Min Act: -0.0000

Data Index: 799606 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1237588 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1117490 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.3798. Min Act: -0.0000

Data Index: 256584 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4107. Min Act: -0.0000

Data Index: 665146 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1743548 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1858297 (The Pile)

Max Activating Token Index: 729