Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4592. Min Act: -0.0001

Data Index: 871077 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1617080 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4474. Min Act: -0.0001

Data Index: 356220 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4530. Min Act: -0.0001

Data Index: 81622 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4489. Min Act: -0.0001

Data Index: 1599468 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4277. Min Act: -0.0001

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4528. Min Act: -0.0001

Data Index: 424441 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1382530 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4053. Min Act: -0.0001

Data Index: 66957 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4207. Min Act: -0.0001

Data Index: 1445666 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4213. Min Act: -0.0001

Data Index: 1407738 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3779. Min Act: -0.0001

Data Index: 1399931 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4294. Min Act: -0.0001

Data Index: 49661 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3842. Min Act: -0.0001

Data Index: 390407 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3855. Min Act: -0.0001

Data Index: 281360 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3923. Min Act: -0.0001

Data Index: 529013 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3620. Min Act: -0.0001

Data Index: 607078 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3724. Min Act: -0.0001

Data Index: 702181 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1138551 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3846. Min Act: -0.0001

Data Index: 495256 (C4 (Web Text))

Max Activating Token Index: 694