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

Dataset: The Pile

Neuron 2861 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1500640 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.1359. Min Act: -0.0000

Data Index: 683434 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9857. Min Act: -0.0000

Data Index: 712537 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1610546 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9947. Min Act: -0.0000

Data Index: 810468 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1419946 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9774. Min Act: -0.0000

Data Index: 476878 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1070133 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1569858 (The Pile)

Max Activating Token Index: 855

Text #9

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8175. Min Act: -0.0000

Data Index: 760344 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1082890 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1874014 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1788859 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8853. Min Act: -0.0000

Data Index: 62102 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9318. Min Act: -0.0000

Data Index: 47008 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1948018 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8327. Min Act: -0.0000

Data Index: 189788 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8830. Min Act: -0.0000

Data Index: 844008 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8601. Min Act: -0.0000

Data Index: 915594 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9079. Min Act: -0.0000

Data Index: 146381 (The Pile)

Max Activating Token Index: 694