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

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

Neuron 280 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: 5.8907. Min Range: -5.8907

Max Act: 5.8907. Min Act: -0.0000

Data Index: 1012004 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.8422. Min Act: -0.0001

Data Index: 1215011 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.4349. Min Act: -0.0000

Data Index: 377837 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.3066. Min Act: -0.0001

Data Index: 340433 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.4675. Min Act: -0.0001

Data Index: 1099798 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.3059. Min Act: -0.0001

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9618. Min Act: -0.0001

Data Index: 101561 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.2986. Min Act: -0.0000

Data Index: 1163168 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9947. Min Act: -0.0001

Data Index: 279973 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9547. Min Act: -0.0001

Data Index: 1335349 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.4622. Min Act: -0.0000

Data Index: 339290 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9266. Min Act: -0.0000

Data Index: 1254087 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 5.8907. Min Range: -5.8907

Max Act: 5.0724. Min Act: -0.0000

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9523. Min Act: -0.0000

Data Index: 467288 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.7019. Min Act: -0.0000

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.8785. Min Act: -0.0001

Data Index: 1165302 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.6954. Min Act: -0.0000

Data Index: 673699 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9923. Min Act: -0.0001

Data Index: 1153716 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.6192. Min Act: -0.0001

Data Index: 406365 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 5.8907. Min Range: -5.8907

Max Act: 4.9256. Min Act: -0.0000

Data Index: 529233 (C4 (Web Text))

Max Activating Token Index: 297