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

Dataset: The Pile

Neuron 2966 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: 0.3439. Min Range: -0.3439

Max Act: 0.3439. Min Act: -0.0000

Data Index: 515751 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1380694 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1494370 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1554320 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1451636 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2068. Min Act: -0.0000

Data Index: 814500 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2034. Min Act: -0.0000

Data Index: 293595 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1745924 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1186326 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1816. Min Act: -0.0000

Data Index: 257724 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2128. Min Act: -0.0000

Data Index: 878279 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1923. Min Act: -0.0000

Data Index: 360630 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1909. Min Act: -0.0000

Data Index: 636579 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1711530 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1893. Min Act: -0.0000

Data Index: 551341 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1706051 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1885. Min Act: -0.0000

Data Index: 671326 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1809. Min Act: -0.0000

Data Index: 575752 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1387012 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1748. Min Act: -0.0000

Data Index: 621193 (The Pile)

Max Activating Token Index: 86