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

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

Neuron 4497 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.8317. Min Act: -0.0000

Data Index: 541309 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7722. Min Act: -0.0000

Data Index: 747802 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7056. Min Act: -0.0000

Data Index: 748834 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7107. Min Act: -0.0000

Data Index: 729605 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1333322 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6761. Min Act: -0.0000

Data Index: 726820 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6228. Min Act: -0.0000

Data Index: 729656 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5847. Min Act: -0.0000

Data Index: 337778 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5438. Min Act: -0.0000

Data Index: 634578 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6138. Min Act: -0.0000

Data Index: 286821 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1182571 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1053840 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5587. Min Act: -0.0000

Data Index: 543874 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5360. Min Act: -0.0000

Data Index: 669668 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5494. Min Act: -0.0000

Data Index: 459410 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1274592 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1136213 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1302536 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1181820 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1322306 (C4 (Web Text))

Max Activating Token Index: 57