Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1327528 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1263345 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0553. Min Act: -0.0003

Data Index: 723537 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0524. Min Act: -0.0004

Data Index: 146091 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0530. Min Act: -0.0003

Data Index: 867083 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0547. Min Act: -0.0003

Data Index: 549697 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1313524 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0509. Min Act: -0.0003

Data Index: 185820 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0484. Min Act: -0.0003

Data Index: 233170 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0507. Min Act: -0.0003

Data Index: 824062 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0475. Min Act: -0.0003

Data Index: 435046 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0488. Min Act: -0.0004

Data Index: 938632 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0470. Min Act: -0.0003

Data Index: 58903 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0474. Min Act: -0.0003

Data Index: 18810 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0483. Min Act: -0.0003

Data Index: 512115 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0490. Min Act: -0.0004

Data Index: 187346 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0488. Min Act: -0.0003

Data Index: 269742 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1351713 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0499. Min Act: -0.0004

Data Index: 970026 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0504. Min Act: -0.0004

Data Index: 733666 (C4 (Web Text))

Max Activating Token Index: 608