Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3128 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.7920. Min Act: -0.0000

Data Index: 386009 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5924. Min Act: -0.0000

Data Index: 1210625 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5606. Min Act: -0.0000

Data Index: 713795 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1601. Min Act: -0.0000

Data Index: 526414 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.7892. Min Act: -0.0000

Data Index: 617875 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.3455. Min Act: -0.0000

Data Index: 196254 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.7644. Min Act: -0.0000

Data Index: 841687 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.2955. Min Act: -0.0000

Data Index: 848291 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5612. Min Act: -0.0000

Data Index: 185262 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5181. Min Act: -0.0000

Data Index: 111972 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.4683. Min Act: -0.0000

Data Index: 1264736 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1920. Min Act: -0.0000

Data Index: 724252 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1046. Min Act: -0.0000

Data Index: 748824 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.4344. Min Act: -0.0000

Data Index: 831156 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.7920. Min Range: -2.7920

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1142262 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0150. Min Act: -0.0000

Data Index: 761462 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0652. Min Act: -0.0000

Data Index: 468128 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1768. Min Act: -0.0000

Data Index: 993717 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 2.7920. Min Range: -2.7920

Max Act: 1.9337. Min Act: -0.0000

Data Index: 633270 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1706. Min Act: -0.0000

Data Index: 1113896 (C4 (Web Text))

Max Activating Token Index: 840