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

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

Neuron 5078 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0003

Data Index: 788548 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1330732 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0625. Min Act: -0.0003

Data Index: 125340 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1265781 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0577. Min Act: -0.0003

Data Index: 139024 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0579. Min Act: -0.0003

Data Index: 49640 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1294900 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0553. Min Act: -0.0003

Data Index: 928287 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0548. Min Act: -0.0003

Data Index: 899252 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0563. Min Act: -0.0003

Data Index: 902835 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0538. Min Act: -0.0003

Data Index: 371918 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1323713 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1142788 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0523. Min Act: -0.0002

Data Index: 534386 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0488. Min Act: -0.0003

Data Index: 894644 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0500. Min Act: -0.0003

Data Index: 459198 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0489. Min Act: -0.0002

Data Index: 822509 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1132769 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0499. Min Act: -0.0003

Data Index: 116085 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0486. Min Act: -0.0003

Data Index: 338853 (C4 (Web Text))

Max Activating Token Index: 1016