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

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

Neuron 5994 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3507. Min Range: -6.3507

Max Act: 6.3507. Min Act: -0.0000

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 6.3507. Min Range: -6.3507

Max Act: 6.0963. Min Act: -0.0000

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 6.3507. Min Range: -6.3507

Max Act: 6.0742. Min Act: -0.0000

Data Index: 430303 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.8725. Min Act: -0.0000

Data Index: 346515 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 6.3507. Min Range: -6.3507

Max Act: 6.0347. Min Act: -0.0000

Data Index: 1042224 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 6.3507. Min Range: -6.3507

Max Act: 6.2004. Min Act: -0.0000

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.9580. Min Act: -0.0000

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.8755. Min Act: -0.0000

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.8078. Min Act: -0.0000

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.7955. Min Act: -0.0000

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.6521. Min Act: -0.0000

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.6133. Min Act: -0.0000

Data Index: 624235 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.6077. Min Act: -0.0000

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.5924. Min Act: -0.0000

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.5796. Min Act: -0.0000

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.7733. Min Act: -0.0000

Data Index: 60054 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.7732. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.5904. Min Act: -0.0000

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.5074. Min Act: -0.0000

Data Index: 651182 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 6.3507. Min Range: -6.3507

Max Act: 5.5018. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 251