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

Dataset: The Pile

Neuron 1392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1414627 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1876102 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6565. Min Act: -0.0000

Data Index: 613535 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6721. Min Act: -0.0000

Data Index: 901263 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1794302 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1900084 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1483814 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6399. Min Act: -0.0000

Data Index: 15994 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1866111 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1013386 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6661. Min Act: -0.0000

Data Index: 343636 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6266. Min Act: -0.0000

Data Index: 9016 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1848029 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6437. Min Act: -0.0000

Data Index: 105315 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1907095 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1830907 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1685741 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1991656 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1225840 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1220247 (The Pile)

Max Activating Token Index: 850