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

Dataset: The Pile

Neuron 3855 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0000

Data Index: 915695 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3057. Min Act: -0.0000

Data Index: 126611 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2960. Min Act: -0.0000

Data Index: 652914 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3136. Min Act: -0.0000

Data Index: 583924 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1066838 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1446129 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1640078 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1577878 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2853. Min Act: -0.0000

Data Index: 536168 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3050. Min Act: -0.0000

Data Index: 385321 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2949. Min Act: -0.0000

Data Index: 642840 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1106816 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1999685 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2713. Min Act: -0.0000

Data Index: 24195 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2836. Min Act: -0.0000

Data Index: 895849 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2791. Min Act: -0.0000

Data Index: 898165 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2730. Min Act: -0.0000

Data Index: 878103 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2720. Min Act: -0.0000

Data Index: 390567 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1455607 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1151999 (The Pile)

Max Activating Token Index: 126