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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 837370 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1444. Min Act: -0.0001

Data Index: 60086 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1010785 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1167. Min Act: -0.0001

Data Index: 730127 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1057132 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0972. Min Act: -0.0001

Data Index: 308335 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1044. Min Act: -0.0001

Data Index: 190174 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1304297 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0943. Min Act: -0.0001

Data Index: 832947 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0928. Min Act: -0.0001

Data Index: 89869 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0958. Min Act: -0.0001

Data Index: 112558 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0866. Min Act: -0.0001

Data Index: 896480 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0711. Min Act: -0.0001

Data Index: 809749 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1200849 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0843. Min Act: -0.0001

Data Index: 669293 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1030348 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1144777 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1612007 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1482096 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1023139 (C4 (Web Text))

Max Activating Token Index: 252