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

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

Neuron 722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1222608 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0738. Min Act: -0.0000

Data Index: 797073 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1097710 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0725. Min Act: -0.0000

Data Index: 510242 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1097345 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0709. Min Act: -0.0000

Data Index: 892311 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1219473 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0684. Min Act: -0.0000

Data Index: 878266 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0584. Min Act: -0.0000

Data Index: 131465 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0569. Min Act: -0.0000

Data Index: 878048 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0654. Min Act: -0.0000

Data Index: 893851 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0524. Min Act: -0.0000

Data Index: 495910 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0585. Min Act: -0.0000

Data Index: 535339 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0558. Min Act: -0.0000

Data Index: 686642 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0577. Min Act: -0.0001

Data Index: 390022 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1089417 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0618. Min Act: -0.0000

Data Index: 909678 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0573. Min Act: -0.0001

Data Index: 872943 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1096654 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0588. Min Act: -0.0001

Data Index: 294872 (C4 (Web Text))

Max Activating Token Index: 417