Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2491 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0545. Min Range: -1.0545

Max Act: 1.0545. Min Act: -0.0001

Data Index: 1391973 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 1.0545. Min Range: -1.0545

Max Act: 1.0056. Min Act: -0.0001

Data Index: 645670 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9810. Min Act: -0.0001

Data Index: 1193553 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9604. Min Act: -0.0001

Data Index: 665743 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9327. Min Act: -0.0001

Data Index: 207372 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8752. Min Act: -0.0001

Data Index: 350425 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8950. Min Act: -0.0001

Data Index: 979100 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9444. Min Act: -0.0001

Data Index: 1205201 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8729. Min Act: -0.0001

Data Index: 174117 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9273. Min Act: -0.0001

Data Index: 612833 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9042. Min Act: -0.0001

Data Index: 594741 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8502. Min Act: -0.0001

Data Index: 104393 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1214238 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9255. Min Act: -0.0001

Data Index: 616431 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8806. Min Act: -0.0001

Data Index: 624591 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8927. Min Act: -0.0001

Data Index: 115803 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8891. Min Act: -0.0001

Data Index: 1535121 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8526. Min Act: -0.0001

Data Index: 936052 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8212. Min Act: -0.0001

Data Index: 594279 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8525. Min Act: -0.0001

Data Index: 722557 (C4 (Web Text))

Max Activating Token Index: 340