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

Dataset: The Pile

Neuron 3538 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: 0.8502. Min Range: -0.8502

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1769124 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1327264 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7693. Min Act: -0.0000

Data Index: 149263 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1710752 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7265. Min Act: -0.0000

Data Index: 396046 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1867752 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1948654 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1118829 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6904. Min Act: -0.0000

Data Index: 843043 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6752. Min Act: -0.0000

Data Index: 925179 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6599. Min Act: -0.0000

Data Index: 696935 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1091512 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5413. Min Act: -0.0000

Data Index: 279549 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6176. Min Act: -0.0000

Data Index: 72329 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5758. Min Act: -0.0000

Data Index: 369335 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1151659 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1659805 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1916369 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5713. Min Act: -0.0000

Data Index: 797430 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.5625. Min Act: -0.0000

Data Index: 100007 (The Pile)

Max Activating Token Index: 179