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

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

Neuron 4643 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1755. Min Range: -1.1755

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1450298 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 1.1755. Min Range: -1.1755

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1618456 (Python Code)

Max Activating Token Index: 831

Text #2

Max Range: 1.1755. Min Range: -1.1755

Max Act: 1.0342. Min Act: -0.0000

Data Index: 370715 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9876. Min Act: -0.0000

Data Index: 120408 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9742. Min Act: -0.0000

Data Index: 243543 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9061. Min Act: -0.0000

Data Index: 771475 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9564. Min Act: -0.0000

Data Index: 454461 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1002955 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1307405 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8841. Min Act: -0.0000

Data Index: 503043 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1323389 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8604. Min Act: -0.0000

Data Index: 985000 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1250230 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.9009. Min Act: -0.0000

Data Index: 535095 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8645. Min Act: -0.0000

Data Index: 684363 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8292. Min Act: -0.0000

Data Index: 566011 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8796. Min Act: -0.0000

Data Index: 224240 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8219. Min Act: -0.0000

Data Index: 493368 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1104677 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.1755. Min Range: -1.1755

Max Act: 0.7998. Min Act: -0.0000

Data Index: 131086 (C4 (Web Text))

Max Activating Token Index: 496