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

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

Neuron 2016 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.8546. Min Act: -0.0000

Data Index: 1080517 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.9190. Min Act: -0.0000

Data Index: 117069 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.6881. Min Act: -0.0000

Data Index: 745872 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.8496. Min Act: -0.0000

Data Index: 428076 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.6934. Min Act: -0.0000

Data Index: 908453 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.7604. Min Act: -0.0000

Data Index: 278648 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.5845. Min Act: -0.0000

Data Index: 1195583 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.6028. Min Act: -0.0000

Data Index: 146723 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.6693. Min Act: -0.0000

Data Index: 407017 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.4037. Min Act: -0.0000

Data Index: 1296047 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.5128. Min Act: -0.0000

Data Index: 290537 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.4919. Min Act: -0.0000

Data Index: 1181266 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.4525. Min Act: -0.0000

Data Index: 153583 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.4261. Min Act: -0.0000

Data Index: 1146703 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.8199. Min Act: -0.0000

Data Index: 421468 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.2811. Min Act: -0.0000

Data Index: 665580 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.2672. Min Act: -0.0000

Data Index: 1045336 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.2715. Min Act: -0.0000

Data Index: 402909 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.4980. Min Act: -0.0000

Data Index: 577824 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.9190. Min Range: -2.9190

Max Act: 2.3082. Min Act: -0.0000

Data Index: 591733 (C4 (Web Text))

Max Activating Token Index: 488