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

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

Neuron 1653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1358863 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0660. Min Act: -0.0001

Data Index: 649518 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0633. Min Act: -0.0001

Data Index: 610525 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0656. Min Act: -0.0001

Data Index: 895214 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0647. Min Act: -0.0001

Data Index: 736812 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0592. Min Act: -0.0001

Data Index: 899542 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0604. Min Act: -0.0001

Data Index: 977357 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0610. Min Act: -0.0001

Data Index: 328152 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1175212 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1189373 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0556. Min Act: -0.0001

Data Index: 822109 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1229884 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1152505 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1045681 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1175006 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0559. Min Act: -0.0001

Data Index: 422299 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1136173 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0534. Min Act: -0.0001

Data Index: 895300 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0539. Min Act: -0.0001

Data Index: 989944 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1213457 (C4 (Web Text))

Max Activating Token Index: 112