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

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

Neuron 3564 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1288307 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6208. Min Act: -0.0000

Data Index: 343598 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5411. Min Act: -0.0000

Data Index: 180845 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5521. Min Act: -0.0000

Data Index: 915910 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4584. Min Act: -0.0000

Data Index: 272759 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1055420 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5005. Min Act: -0.0000

Data Index: 789325 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1532888 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5134. Min Act: -0.0000

Data Index: 228581 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6635. Min Act: -0.0000

Data Index: 56257 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1057878 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4718. Min Act: -0.0000

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5329. Min Act: -0.0000

Data Index: 965892 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1653303 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1081188 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4045. Min Act: -0.0000

Data Index: 163989 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6419. Min Act: -0.0000

Data Index: 783444 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1254471 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1238695 (C4 (Web Text))

Max Activating Token Index: 327