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

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

Neuron 1054 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: 2.9919. Min Range: -2.9919

Max Act: 2.9919. Min Act: -0.0000

Data Index: 733850 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.7748. Min Act: -0.0001

Data Index: 513340 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4048. Min Act: -0.0001

Data Index: 801647 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 2.9919. Min Range: -2.9919

Max Act: 1.9684. Min Act: -0.0000

Data Index: 379031 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1333731 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.2507. Min Act: -0.0000

Data Index: 1078386 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.2112. Min Act: -0.0000

Data Index: 1336686 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1822. Min Act: -0.0000

Data Index: 310110 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1576. Min Act: -0.0000

Data Index: 552549 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0599. Min Act: -0.0001

Data Index: 780242 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0439. Min Act: -0.0000

Data Index: 106331 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1392. Min Act: -0.0001

Data Index: 736526 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1445. Min Act: -0.0000

Data Index: 19016 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1221. Min Act: -0.0000

Data Index: 289596 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0955. Min Act: -0.0000

Data Index: 793633 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0812. Min Act: -0.0001

Data Index: 144111 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 2.9919. Min Range: -2.9919

Max Act: 1.9713. Min Act: -0.0000

Data Index: 1023806 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0622. Min Act: -0.0001

Data Index: 689922 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.0677. Min Act: -0.0000

Data Index: 655552 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 2.9919. Min Range: -2.9919

Max Act: 1.9497. Min Act: -0.0001

Data Index: 1025680 (C4 (Web Text))

Max Activating Token Index: 391