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

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

Neuron 2875 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.6739. Min Act: 0.0000

Data Index: 41696 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1441296 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1025877 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1954. Min Act: 0.0000

Data Index: 153454 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.0913. Min Act: -0.0000

Data Index: 144852 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1384. Min Act: -0.0000

Data Index: 916411 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1919. Min Act: -0.0000

Data Index: 984862 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1443628 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1244229 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1403539 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1092715 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.0408. Min Act: -0.0000

Data Index: 194634 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1893 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.6739. Min Range: -1.6739

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1418244 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9847. Min Act: -0.0000

Data Index: 632141 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9627. Min Act: 0.0000

Data Index: 409855 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1482396 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1199681 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1331528 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.6739. Min Range: -1.6739

Max Act: 0.9055. Min Act: -0.0000

Data Index: 384016 (C4 (Web Text))

Max Activating Token Index: 253