Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.2295. Min Act: -0.0000

Data Index: 550970 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1635937 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.1325. Min Act: -0.0000

Data Index: 34182 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1450519 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1531667 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1400112 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0649. Min Act: -0.0000

Data Index: 949806 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1365527 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1404537 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1561638 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9838. Min Act: -0.0000

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1504088 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1320296 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9575. Min Act: -0.0000

Data Index: 53886 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1646637 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1320706 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8588. Min Act: -0.0000

Data Index: 747616 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1491148 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1292157 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8746. Min Act: -0.0000

Data Index: 62831 (C4 (Web Text))

Max Activating Token Index: 1020