Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 941 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1243806 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1625. Min Act: -0.0001

Data Index: 58001 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1651. Min Act: -0.0001

Data Index: 59887 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1590. Min Act: -0.0001

Data Index: 463745 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1512. Min Act: -0.0001

Data Index: 139845 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1537. Min Act: -0.0001

Data Index: 712520 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1491. Min Act: -0.0001

Data Index: 925611 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1489. Min Act: -0.0001

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1500. Min Act: -0.0001

Data Index: 493936 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1205538 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1462. Min Act: -0.0001

Data Index: 247060 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1464. Min Act: -0.0001

Data Index: 652132 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1447. Min Act: -0.0001

Data Index: 332292 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1090034 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1476759 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1509. Min Act: -0.0001

Data Index: 544630 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1011731 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1414. Min Act: -0.0001

Data Index: 212812 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1406. Min Act: -0.0001

Data Index: 185460 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1112574 (C4 (Web Text))

Max Activating Token Index: 116