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

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

Neuron 3008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7816. Min Act: -0.0001

Data Index: 745171 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.3880. Min Act: -0.0001

Data Index: 570371 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.4211. Min Act: -0.0001

Data Index: 498008 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.2845. Min Act: -0.0001

Data Index: 527494 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.0979. Min Act: -0.0001

Data Index: 923691 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.0340. Min Act: -0.0001

Data Index: 178994 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.1851. Min Act: -0.0001

Data Index: 228485 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.9927. Min Act: -0.0001

Data Index: 52306 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.1520. Min Act: -0.0001

Data Index: 567163 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.2554. Min Act: -0.0001

Data Index: 868400 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.1215. Min Act: -0.0001

Data Index: 461485 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.8028. Min Act: -0.0001

Data Index: 602724 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.9027. Min Act: -0.0001

Data Index: 1084613 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.8964. Min Act: -0.0001

Data Index: 396266 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.7255. Min Act: -0.0001

Data Index: 985825 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.8073. Min Act: -0.0001

Data Index: 974111 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.9353. Min Act: -0.0001

Data Index: 1126173 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.7821. Min Act: -0.0001

Data Index: 65589 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.8729. Min Act: -0.0001

Data Index: 614549 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 3.7816. Min Range: -3.7816

Max Act: 2.7131. Min Act: -0.0001

Data Index: 1213240 (C4 (Web Text))

Max Activating Token Index: 449