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

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

Neuron 679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1173320 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1093166 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1122483 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3418. Min Act: -0.0000

Data Index: 182385 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3548. Min Act: -0.0000

Data Index: 555158 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1204915 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3882. Min Act: -0.0000

Data Index: 173454 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2869. Min Act: -0.0000

Data Index: 711494 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1331168 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2572. Min Act: -0.0000

Data Index: 720325 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2782. Min Act: -0.0000

Data Index: 281490 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2754. Min Act: -0.0000

Data Index: 488836 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2782. Min Act: -0.0000

Data Index: 238618 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3061. Min Act: -0.0000

Data Index: 988422 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.1822. Min Act: -0.0000

Data Index: 190590 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2087. Min Act: -0.0000

Data Index: 583454 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1172614 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2113. Min Act: -0.0000

Data Index: 535177 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1262504 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.1618. Min Act: -0.0000

Data Index: 931230 (C4 (Web Text))

Max Activating Token Index: 635