Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3554 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.7880. Min Act: -0.0000

Data Index: 307889 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1010024 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.3750. Min Act: -0.0000

Data Index: 879640 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.1741. Min Act: -0.0000

Data Index: 136974 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.2146. Min Act: -0.0000

Data Index: 135577 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.0639. Min Act: -0.0000

Data Index: 929223 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1158035 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.0335. Min Act: -0.0000

Data Index: 686189 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1011349 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.9468. Min Act: -0.0000

Data Index: 993140 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.9126. Min Act: -0.0000

Data Index: 883960 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8894. Min Act: -0.0000

Data Index: 27553 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8587. Min Act: -0.0000

Data Index: 818846 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1235927 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8905. Min Act: -0.0000

Data Index: 422795 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8496. Min Act: -0.0000

Data Index: 634541 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8267. Min Act: -0.0000

Data Index: 432975 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8411. Min Act: -0.0000

Data Index: 147494 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1101753 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.7880. Min Range: -1.7880

Max Act: 0.7896. Min Act: -0.0000

Data Index: 503680 (C4 (Web Text))

Max Activating Token Index: 433