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

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

Neuron 5499 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: 1.1519. Min Range: -1.1519

Max Act: 1.1519. Min Act: 0.0000

Data Index: 868571 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.1124. Min Act: -0.0000

Data Index: 377734 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0416. Min Act: -0.0000

Data Index: 69449 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0174. Min Act: -0.0000

Data Index: 254403 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1093340 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1078162 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9383. Min Act: -0.0000

Data Index: 351201 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0013. Min Act: -0.0000

Data Index: 466514 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8804. Min Act: -0.0000

Data Index: 723928 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8694. Min Act: -0.0000

Data Index: 139764 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.6026. Min Act: -0.0000

Data Index: 805042 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8336. Min Act: -0.0000

Data Index: 421138 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1170753 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.7918. Min Act: 0.0000

Data Index: 412329 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1471714 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8627. Min Act: -0.0000

Data Index: 294481 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.7980. Min Act: -0.0000

Data Index: 410917 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8008. Min Act: 0.0000

Data Index: 190821 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.7308. Min Act: -0.0000

Data Index: 757007 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.7365. Min Act: -0.0000

Data Index: 4833 (C4 (Web Text))

Max Activating Token Index: 971