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

Dataset: The Pile

Neuron 2151 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1267916 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1917424 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1780746 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8526. Min Act: -0.0000

Data Index: 230442 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1396497 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8411. Min Act: -0.0000

Data Index: 586376 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7829. Min Act: -0.0000

Data Index: 708341 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1730271 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7730. Min Act: -0.0000

Data Index: 768297 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7385. Min Act: -0.0000

Data Index: 551714 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6448. Min Act: -0.0000

Data Index: 425551 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1409085 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6510. Min Act: -0.0000

Data Index: 319643 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6319. Min Act: -0.0000

Data Index: 938723 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6633. Min Act: -0.0000

Data Index: 477064 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6360. Min Act: -0.0000

Data Index: 459796 (The Pile)

Max Activating Token Index: 992

Text #16

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6541. Min Act: -0.0000

Data Index: 632013 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1264378 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1215630 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5420. Min Act: -0.0000

Data Index: 837508 (The Pile)

Max Activating Token Index: 617