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

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

Neuron 3580 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.7123. Min Act: -0.0001

Data Index: 444195 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5795. Min Act: -0.0001

Data Index: 560664 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.2063. Min Act: -0.0001

Data Index: 311753 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.1989. Min Act: -0.0001

Data Index: 1035352 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.8699. Min Act: -0.0001

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.0199. Min Act: -0.0001

Data Index: 1041083 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7435. Min Act: -0.0001

Data Index: 159658 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.8066. Min Act: -0.0001

Data Index: 480212 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7523. Min Act: -0.0001

Data Index: 674649 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.9670. Min Act: -0.0001

Data Index: 411358 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.6876. Min Act: -0.0001

Data Index: 409742 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.8102. Min Act: -0.0001

Data Index: 521446 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7860. Min Act: -0.0001

Data Index: 442675 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7842. Min Act: -0.0001

Data Index: 907991 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.6928. Min Act: -0.0001

Data Index: 1073815 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7509. Min Act: -0.0001

Data Index: 702720 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.5615. Min Act: -0.0001

Data Index: 980143 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.7627. Min Act: -0.0001

Data Index: 709176 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.6109. Min Act: -0.0001

Data Index: 16750 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.7123. Min Range: -3.7123

Max Act: 2.4411. Min Act: -0.0001

Data Index: 602152 (C4 (Web Text))

Max Activating Token Index: 132