Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2584 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8466. Min Act: -0.0003

Data Index: 1335935 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8232. Min Act: -0.0003

Data Index: 1121698 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8952. Min Act: -0.0003

Data Index: 697188 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7568. Min Act: -0.0003

Data Index: 597644 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7010. Min Act: -0.0003

Data Index: 404631 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8060. Min Act: -0.0003

Data Index: 746140 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6389. Min Act: -0.0003

Data Index: 403929 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7199. Min Act: -0.0003

Data Index: 54413 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7453. Min Act: -0.0003

Data Index: 1233820 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7879. Min Act: -0.0003

Data Index: 184349 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6968. Min Act: -0.0003

Data Index: 759980 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6997. Min Act: -0.0003

Data Index: 375524 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6947. Min Act: -0.0003

Data Index: 914571 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7029. Min Act: -0.0003

Data Index: 195740 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6584. Min Act: -0.0003

Data Index: 1235089 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.5073. Min Act: -0.0003

Data Index: 255121 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.5659. Min Act: -0.0003

Data Index: 1152946 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6796. Min Act: -0.0003

Data Index: 1151808 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.5195. Min Act: -0.0003

Data Index: 537535 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7008. Min Act: -0.0003

Data Index: 727810 (C4 (Web Text))

Max Activating Token Index: 934