Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 525 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1354039 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0707. Min Act: -0.0002

Data Index: 335651 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0664. Min Act: -0.0002

Data Index: 855827 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1243626 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0617. Min Act: -0.0002

Data Index: 348741 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0604. Min Act: -0.0002

Data Index: 978115 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0592. Min Act: -0.0002

Data Index: 599312 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0535. Min Act: -0.0002

Data Index: 162258 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1117380 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0546. Min Act: -0.0002

Data Index: 528076 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0495. Min Act: -0.0002

Data Index: 280879 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0508. Min Act: -0.0002

Data Index: 805030 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1234007 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1140821 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0499. Min Act: -0.0002

Data Index: 597847 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1053042 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1340736 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0474. Min Act: -0.0002

Data Index: 631105 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0470. Min Act: -0.0002

Data Index: 666135 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0482. Min Act: -0.0002

Data Index: 599535 (C4 (Web Text))

Max Activating Token Index: 573