Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0001

Data Index: 365379 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5785. Min Act: -0.0001

Data Index: 264121 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5195. Min Act: -0.0001

Data Index: 348040 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5400. Min Act: -0.0001

Data Index: 1238119 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5016. Min Act: -0.0001

Data Index: 879154 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1132015 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5209. Min Act: -0.0001

Data Index: 409555 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4742. Min Act: -0.0001

Data Index: 1211658 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4912. Min Act: -0.0001

Data Index: 439737 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5008. Min Act: -0.0001

Data Index: 738571 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4697. Min Act: -0.0001

Data Index: 1066976 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4912. Min Act: -0.0001

Data Index: 399492 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4752. Min Act: -0.0001

Data Index: 858360 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4724. Min Act: -0.0001

Data Index: 230639 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4569. Min Act: -0.0001

Data Index: 896533 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4861. Min Act: -0.0001

Data Index: 123615 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1253348 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4662. Min Act: -0.0001

Data Index: 699681 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1019784 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4328. Min Act: -0.0001

Data Index: 133999 (C4 (Web Text))

Max Activating Token Index: 321