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

Dataset: The Pile

Neuron 5033 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: 0.2439. Min Range: -0.2439

Max Act: 0.2439. Min Act: -0.0000

Data Index: 560305 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1210519 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2260. Min Act: -0.0000

Data Index: 790156 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1961. Min Act: -0.0000

Data Index: 75934 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1808. Min Act: -0.0000

Data Index: 619038 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1875. Min Act: -0.0000

Data Index: 951506 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1105700 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1987108 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1574. Min Act: -0.0000

Data Index: 24935 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1706113 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1727. Min Act: -0.0000

Data Index: 436894 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1498. Min Act: -0.0000

Data Index: 418229 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1245636 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1054375 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1734. Min Act: -0.0000

Data Index: 331351 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1491. Min Act: -0.0000

Data Index: 810780 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1458646 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1626. Min Act: -0.0000

Data Index: 148263 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1517. Min Act: -0.0000

Data Index: 451093 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1829672 (The Pile)

Max Activating Token Index: 430