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

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

Neuron 5412 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1818. Min Range: -5.1818

Max Act: 5.1818. Min Act: -0.0001

Data Index: 1402152 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.5408. Min Act: -0.0001

Data Index: 1589407 (Python Code)

Max Activating Token Index: 411

Text #2

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.4464. Min Act: -0.0001

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.4195. Min Act: -0.0001

Data Index: 1633212 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.4683. Min Act: -0.0001

Data Index: 859623 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.9116. Min Act: -0.0000

Data Index: 111083 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8782. Min Act: -0.0001

Data Index: 1347865 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.0064. Min Act: -0.0001

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 5.1818. Min Range: -5.1818

Max Act: 4.0108. Min Act: -0.0001

Data Index: 1244551 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.9778. Min Act: -0.0001

Data Index: 927524 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.9817. Min Act: -0.0001

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8073. Min Act: -0.0001

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.9635. Min Act: -0.0001

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8499. Min Act: -0.0001

Data Index: 670849 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8204. Min Act: -0.0001

Data Index: 89472 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8019. Min Act: -0.0001

Data Index: 384871 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.8527. Min Act: -0.0000

Data Index: 1563518 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.4527. Min Act: -0.0001

Data Index: 1404747 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.3944. Min Act: -0.0000

Data Index: 802393 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 5.1818. Min Range: -5.1818

Max Act: 3.9042. Min Act: -0.0001

Data Index: 383620 (C4 (Web Text))

Max Activating Token Index: 644