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

Dataset: The Pile

Neuron 3301 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: 5.0874. Min Range: -5.0874

Max Act: 5.0874. Min Act: -0.0000

Data Index: 1818660 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 5.0874. Min Range: -5.0874

Max Act: 4.3010. Min Act: -0.0000

Data Index: 808791 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.8439. Min Act: -0.0000

Data Index: 489841 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.1854. Min Act: -0.0000

Data Index: 1476058 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.2457. Min Act: -0.0000

Data Index: 1172645 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.0054. Min Act: -0.0000

Data Index: 1356090 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.1260. Min Act: -0.0000

Data Index: 1398200 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.0606. Min Act: -0.0000

Data Index: 1826142 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.0850. Min Act: -0.0000

Data Index: 431339 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.7738. Min Act: -0.0000

Data Index: 382984 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 5.0874. Min Range: -5.0874

Max Act: 3.0300. Min Act: -0.0000

Data Index: 1961536 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.9935. Min Act: -0.0000

Data Index: 871015 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.7105. Min Act: -0.0000

Data Index: 1857005 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.9828. Min Act: -0.0000

Data Index: 1049353 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.8287. Min Act: -0.0000

Data Index: 1293724 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.9542. Min Act: -0.0000

Data Index: 239965 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.4253. Min Act: -0.0000

Data Index: 520158 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.7797. Min Act: -0.0000

Data Index: 312549 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.7071. Min Act: -0.0000

Data Index: 390893 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 5.0874. Min Range: -5.0874

Max Act: 2.7056. Min Act: -0.0000

Data Index: 633747 (The Pile)

Max Activating Token Index: 430