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

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

Neuron 781 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: 0.9741. Min Range: -0.9741

Max Act: 0.9111. Min Act: -0.0001

Data Index: 632412 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0001

Data Index: 496469 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9455. Min Act: -0.0001

Data Index: 884218 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8563. Min Act: -0.0001

Data Index: 1357420 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8910. Min Act: -0.0001

Data Index: 1330518 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8119. Min Act: -0.0001

Data Index: 1312726 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8635. Min Act: -0.0001

Data Index: 678883 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8498. Min Act: -0.0001

Data Index: 907217 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7909. Min Act: -0.0001

Data Index: 791756 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8627. Min Act: -0.0001

Data Index: 999523 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8254. Min Act: -0.0001

Data Index: 29146 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7706. Min Act: -0.0001

Data Index: 392748 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8389. Min Act: -0.0001

Data Index: 395647 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1284219 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7636. Min Act: -0.0001

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1178982 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7450. Min Act: -0.0001

Data Index: 314841 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7433. Min Act: -0.0001

Data Index: 8943 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1297845 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8081. Min Act: -0.0001

Data Index: 1215958 (C4 (Web Text))

Max Activating Token Index: 873