Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1421 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.8572. Min Act: -0.0001

Data Index: 573821 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.8304. Min Act: -0.0001

Data Index: 940411 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.8152. Min Act: -0.0002

Data Index: 899557 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.8021. Min Act: -0.0001

Data Index: 94688 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.8071. Min Act: -0.0001

Data Index: 266121 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7891. Min Act: -0.0001

Data Index: 642839 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7989. Min Act: -0.0002

Data Index: 926015 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7883. Min Act: -0.0001

Data Index: 1261411 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7771. Min Act: -0.0001

Data Index: 778962 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7698. Min Act: -0.0001

Data Index: 752609 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7676. Min Act: -0.0001

Data Index: 824536 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7626. Min Act: -0.0001

Data Index: 283156 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7533. Min Act: -0.0001

Data Index: 491980 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7507. Min Act: -0.0002

Data Index: 779841 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7519. Min Act: -0.0001

Data Index: 471878 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7497. Min Act: -0.0001

Data Index: 1304434 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1105770 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7522. Min Act: -0.0001

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7628. Min Act: -0.0001

Data Index: 971640 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.8572. Min Range: -0.8572

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1042493 (C4 (Web Text))

Max Activating Token Index: 830