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

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

Neuron 1921 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.8028. Min Act: -0.0001

Data Index: 709590 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.8027. Min Act: -0.0001

Data Index: 317709 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.7049. Min Act: -0.0001

Data Index: 1448840 (Python Code)

Max Activating Token Index: 895

Text #3

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1272691 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.5857. Min Act: -0.0001

Data Index: 1595204 (Python Code)

Max Activating Token Index: 866

Text #5

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1532630 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6595. Min Act: -0.0001

Data Index: 68197 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6038. Min Act: -0.0001

Data Index: 188062 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6547. Min Act: -0.0001

Data Index: 449227 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6555. Min Act: -0.0001

Data Index: 1030868 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1541009 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1295846 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6276. Min Act: -0.0001

Data Index: 1409064 (Python Code)

Max Activating Token Index: 776

Text #13

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1534512 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1573738 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6799. Min Act: -0.0001

Data Index: 524002 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6557. Min Act: -0.0001

Data Index: 521312 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.5963. Min Act: -0.0001

Data Index: 569304 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.6174. Min Act: -0.0001

Data Index: 419430 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.8028. Min Range: -0.8028

Max Act: 0.5720. Min Act: -0.0001

Data Index: 874292 (C4 (Web Text))

Max Activating Token Index: 926