Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 665 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0005

Data Index: 490284 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0378. Min Act: -0.0005

Data Index: 817653 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0362. Min Act: -0.0005

Data Index: 55541 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0356. Min Act: -0.0005

Data Index: 127060 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0368. Min Act: -0.0005

Data Index: 971937 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0341. Min Act: -0.0005

Data Index: 365028 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0347. Min Act: -0.0005

Data Index: 376578 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0339. Min Act: -0.0005

Data Index: 591647 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0331. Min Act: -0.0005

Data Index: 580498 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0337. Min Act: -0.0005

Data Index: 574409 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0331. Min Act: -0.0005

Data Index: 761972 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0330. Min Act: -0.0005

Data Index: 454963 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0330. Min Act: -0.0004

Data Index: 936829 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0336. Min Act: -0.0005

Data Index: 397551 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1086444 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0325. Min Act: -0.0005

Data Index: 965864 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0317. Min Act: -0.0005

Data Index: 911431 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0313. Min Act: -0.0004

Data Index: 179002 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0316. Min Act: -0.0005

Data Index: 465237 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0314. Min Act: -0.0005

Data Index: 557384 (C4 (Web Text))

Max Activating Token Index: 961