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

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

Neuron 2458 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: 1.9605. Min Range: -1.9605

Max Act: 1.8850. Min Act: -0.0001

Data Index: 1061288 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.8847. Min Act: -0.0001

Data Index: 336695 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.8848. Min Act: -0.0001

Data Index: 533473 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.7038. Min Act: -0.0001

Data Index: 1282916 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.9605. Min Act: -0.0001

Data Index: 945016 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5636. Min Act: -0.0001

Data Index: 241406 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4874. Min Act: -0.0001

Data Index: 1331963 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4968. Min Act: -0.0001

Data Index: 983715 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5375. Min Act: -0.0001

Data Index: 1069867 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5502. Min Act: -0.0001

Data Index: 118563 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5218. Min Act: -0.0001

Data Index: 596376 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.6080. Min Act: -0.0001

Data Index: 1259523 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4345. Min Act: -0.0001

Data Index: 363122 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5869. Min Act: -0.0001

Data Index: 1041721 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5030. Min Act: -0.0001

Data Index: 690174 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5567. Min Act: -0.0001

Data Index: 726565 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5120. Min Act: -0.0001

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4156. Min Act: -0.0001

Data Index: 488810 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4155. Min Act: -0.0001

Data Index: 999899 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3772. Min Act: -0.0001

Data Index: 712196 (C4 (Web Text))

Max Activating Token Index: 135