Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2173 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1071827 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0711. Min Act: -0.0000

Data Index: 624756 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0668. Min Act: -0.0000

Data Index: 652736 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0641. Min Act: -0.0000

Data Index: 805305 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0609. Min Act: -0.0000

Data Index: 475156 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1327581 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0606. Min Act: -0.0001

Data Index: 158473 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1288794 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1248172 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1085172 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0565. Min Act: -0.0000

Data Index: 355560 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0541. Min Act: -0.0001

Data Index: 160016 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0534. Min Act: -0.0000

Data Index: 496944 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0535. Min Act: -0.0000

Data Index: 878053 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0532. Min Act: -0.0001

Data Index: 552566 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1049312 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0524. Min Act: -0.0000

Data Index: 216184 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0556. Min Act: -0.0000

Data Index: 703382 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1154717 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0550. Min Act: -0.0000

Data Index: 900608 (C4 (Web Text))

Max Activating Token Index: 581