Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4971 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1124208 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0538. Min Act: -0.0001

Data Index: 776461 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0523. Min Act: -0.0001

Data Index: 598052 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1054260 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0433. Min Act: -0.0001

Data Index: 839597 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0458. Min Act: -0.0001

Data Index: 109551 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0405. Min Act: -0.0001

Data Index: 139901 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0446. Min Act: -0.0001

Data Index: 193028 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1197106 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0415. Min Act: -0.0001

Data Index: 637808 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1162581 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0411. Min Act: -0.0001

Data Index: 564001 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1149265 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0409. Min Act: -0.0001

Data Index: 540853 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1205117 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0365. Min Act: -0.0001

Data Index: 978707 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0408. Min Act: -0.0001

Data Index: 261197 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1017891 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1042581 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0452. Min Act: -0.0001

Data Index: 612612 (C4 (Web Text))

Max Activating Token Index: 598