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

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

Neuron 2726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.2146. Min Act: -0.0001

Data Index: 368082 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1881. Min Act: -0.0001

Data Index: 305477 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1842. Min Act: -0.0001

Data Index: 321495 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1751. Min Act: -0.0001

Data Index: 597979 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1687. Min Act: 0.0000

Data Index: 307147 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1676. Min Act: -0.0000

Data Index: 773025 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1720. Min Act: -0.0001

Data Index: 778723 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1719. Min Act: 0.0002

Data Index: 1160085 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1695. Min Act: -0.0001

Data Index: 757437 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1657. Min Act: -0.0001

Data Index: 678888 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1673. Min Act: 0.0001

Data Index: 34903 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1356238 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1634. Min Act: -0.0000

Data Index: 436724 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1635. Min Act: -0.0000

Data Index: 680739 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1688. Min Act: -0.0001

Data Index: 370061 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1047561 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1597. Min Act: -0.0000

Data Index: 973481 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1604. Min Act: 0.0000

Data Index: 1211401 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1600. Min Act: -0.0001

Data Index: 371936 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.1574. Min Act: -0.0001

Data Index: 419368 (C4 (Web Text))

Max Activating Token Index: 145