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

Dataset: The Pile

Neuron 2069 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: 1.4880. Min Range: -1.4880

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1456811 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1119984 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.3736. Min Act: -0.0000

Data Index: 299360 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.2294. Min Act: -0.0000

Data Index: 618476 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.2582. Min Act: -0.0000

Data Index: 361845 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1591. Min Act: -0.0000

Data Index: 495244 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1325. Min Act: -0.0000

Data Index: 103750 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1464923 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1811334 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1068372 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1015211 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1878054 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0577. Min Act: -0.0000

Data Index: 349964 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1485286 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1579884 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1674425 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1394249 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1789418 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 1.4880. Min Range: -1.4880

Max Act: 1.1381. Min Act: -0.0000

Data Index: 869561 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.4880. Min Range: -1.4880

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1649872 (The Pile)

Max Activating Token Index: 512