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

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

Neuron 712 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: 7.1582. Min Range: -7.1582

Max Act: 7.1582. Min Act: -0.0001

Data Index: 1036042 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 7.1582. Min Range: -7.1582

Max Act: 6.5089. Min Act: -0.0001

Data Index: 679894 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 7.1582. Min Range: -7.1582

Max Act: 6.3640. Min Act: -0.0001

Data Index: 232319 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.1568. Min Act: -0.0001

Data Index: 1186925 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.4846. Min Act: -0.0001

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.2798. Min Act: -0.0001

Data Index: 1222038 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.2684. Min Act: -0.0001

Data Index: 897847 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.2392. Min Act: -0.0001

Data Index: 1110404 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.2348. Min Act: -0.0001

Data Index: 120116 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.1811. Min Act: -0.0001

Data Index: 96504 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.9658. Min Act: -0.0001

Data Index: 667942 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.0604. Min Act: -0.0000

Data Index: 699965 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.2730. Min Act: -0.0001

Data Index: 287443 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.8783. Min Act: -0.0001

Data Index: 1026568 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.9790. Min Act: -0.0001

Data Index: 632231 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 7.1582. Min Range: -7.1582

Max Act: 5.0029. Min Act: -0.0001

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.6451. Min Act: -0.0001

Data Index: 721268 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.9512. Min Act: -0.0001

Data Index: 828919 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.8233. Min Act: -0.0001

Data Index: 381974 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 7.1582. Min Range: -7.1582

Max Act: 4.7806. Min Act: -0.0001

Data Index: 202881 (C4 (Web Text))

Max Activating Token Index: 160