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

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

Neuron 4623 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: 1.4562. Min Range: -1.4562

Max Act: 1.4562. Min Act: -0.0000

Data Index: 637184 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.3655. Min Act: -0.0000

Data Index: 926720 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.2588. Min Act: -0.0000

Data Index: 421011 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1095233 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0618. Min Act: -0.0000

Data Index: 254691 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0970. Min Act: -0.0000

Data Index: 795756 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1203545 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1349632 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9550. Min Act: -0.0000

Data Index: 322596 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1345783 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1103334 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.8866. Min Act: -0.0000

Data Index: 66410 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.8082. Min Act: -0.0000

Data Index: 969347 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7367. Min Act: -0.0000

Data Index: 977030 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7729. Min Act: -0.0000

Data Index: 127935 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7735. Min Act: -0.0000

Data Index: 160989 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7659. Min Act: -0.0000

Data Index: 567496 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7015. Min Act: -0.0000

Data Index: 155182 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.6552. Min Act: -0.0000

Data Index: 3560 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.7083. Min Act: -0.0000

Data Index: 103617 (C4 (Web Text))

Max Activating Token Index: 91