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

Dataset: The Pile

Neuron 2315 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: 0.6661. Min Range: -0.6661

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1546228 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1450334 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6474. Min Act: -0.0000

Data Index: 460814 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1735947 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1976293 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5604. Min Act: -0.0000

Data Index: 253556 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1786265 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1660801 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1531820 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5318. Min Act: -0.0000

Data Index: 884206 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1360753 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5064. Min Act: -0.0000

Data Index: 474708 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5534. Min Act: -0.0000

Data Index: 568723 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1250101 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5579. Min Act: -0.0000

Data Index: 806899 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5098. Min Act: -0.0000

Data Index: 681816 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4778. Min Act: -0.0000

Data Index: 41294 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5245. Min Act: -0.0000

Data Index: 569078 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1255168 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1588381 (The Pile)

Max Activating Token Index: 831