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

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

Neuron 2476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0000

Data Index: 75967 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0599. Min Act: -0.0000

Data Index: 660035 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0556. Min Act: -0.0000

Data Index: 590458 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0478. Min Act: -0.0001

Data Index: 282006 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0449. Min Act: -0.0000

Data Index: 254941 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0440. Min Act: -0.0000

Data Index: 631672 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0430. Min Act: -0.0000

Data Index: 591881 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0432. Min Act: -0.0000

Data Index: 702529 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1111200 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0447. Min Act: -0.0000

Data Index: 35321 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0454. Min Act: -0.0001

Data Index: 35730 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0435. Min Act: -0.0001

Data Index: 632910 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1331441 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0416. Min Act: -0.0001

Data Index: 351179 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0406. Min Act: -0.0000

Data Index: 4706 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0421. Min Act: -0.0000

Data Index: 821026 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0432. Min Act: -0.0000

Data Index: 464636 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0393. Min Act: -0.0000

Data Index: 868955 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1303755 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1028940 (C4 (Web Text))

Max Activating Token Index: 400