Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.8549. Min Act: -0.0000

Data Index: 423616 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1838281 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1839682 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1285853 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7375. Min Act: -0.0000

Data Index: 32701 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7258. Min Act: -0.0000

Data Index: 253531 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6900. Min Act: -0.0000

Data Index: 697043 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6611. Min Act: -0.0000

Data Index: 529513 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6694. Min Act: -0.0000

Data Index: 929181 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6806. Min Act: -0.0000

Data Index: 573918 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1487014 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1977142 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6858. Min Act: -0.0000

Data Index: 443069 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6646. Min Act: -0.0000

Data Index: 689702 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1976429 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1703199 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1107040 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1535108 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6678. Min Act: -0.0000

Data Index: 706512 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1257464 (The Pile)

Max Activating Token Index: 455