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

Dataset: The Pile

Neuron 1126 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3793. Min Act: -0.0000

Data Index: 105064 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1171209 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3196. Min Act: -0.0000

Data Index: 194885 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1239564 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1113824 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2976. Min Act: -0.0000

Data Index: 402148 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1975009 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1496054 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2970. Min Act: -0.0000

Data Index: 380170 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3358. Min Act: -0.0000

Data Index: 553802 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2956. Min Act: -0.0000

Data Index: 605924 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2867. Min Act: -0.0000

Data Index: 849741 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2790. Min Act: -0.0000

Data Index: 432617 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1694880 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2760. Min Act: -0.0000

Data Index: 868319 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1604180 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2694. Min Act: -0.0000

Data Index: 667743 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2934. Min Act: -0.0000

Data Index: 122638 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1117716 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2829. Min Act: -0.0000

Data Index: 530665 (The Pile)

Max Activating Token Index: 698