Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3519 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.7645. Min Act: -0.0001

Data Index: 679974 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.9092. Min Act: -0.0001

Data Index: 1170583 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.8588. Min Act: -0.0001

Data Index: 353374 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.7202. Min Act: -0.0001

Data Index: 464964 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.7081. Min Act: -0.0001

Data Index: 762387 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.6877. Min Act: -0.0001

Data Index: 426656 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.5609. Min Act: -0.0001

Data Index: 679494 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4973. Min Act: -0.0001

Data Index: 337569 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4445. Min Act: -0.0001

Data Index: 493166 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.6818. Min Act: -0.0001

Data Index: 420153 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4572. Min Act: -0.0001

Data Index: 440978 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.5483. Min Act: -0.0001

Data Index: 1229175 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.5757. Min Act: -0.0001

Data Index: 1122500 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.5667. Min Act: -0.0001

Data Index: 142175 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.5690. Min Act: -0.0001

Data Index: 446722 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4824. Min Act: -0.0001

Data Index: 870148 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4591. Min Act: -0.0001

Data Index: 1240581 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4497. Min Act: -0.0001

Data Index: 1187393 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.4033. Min Act: -0.0001

Data Index: 451528 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.9092. Min Range: -1.9092

Max Act: 1.3932. Min Act: -0.0001

Data Index: 1250784 (C4 (Web Text))

Max Activating Token Index: 901