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

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

Neuron 2446 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.3196. Min Act: -0.0001

Data Index: 326641 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1012265 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.2923. Min Act: -0.0000

Data Index: 139043 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.2912. Min Act: -0.0000

Data Index: 435112 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.3025. Min Act: -0.0000

Data Index: 401647 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.2723. Min Act: -0.0000

Data Index: 300574 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1570. Min Act: -0.0000

Data Index: 310058 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1576. Min Act: -0.0000

Data Index: 1085721 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.0215. Min Act: -0.0000

Data Index: 28950 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.0289. Min Act: -0.0000

Data Index: 1035206 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1567. Min Act: -0.0000

Data Index: 1245890 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1530. Min Act: -0.0000

Data Index: 218027 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1535. Min Act: -0.0000

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1734. Min Act: -0.0000

Data Index: 422262 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.0031. Min Act: -0.0000

Data Index: 1201771 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1476. Min Act: -0.0000

Data Index: 536394 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1505. Min Act: -0.0000

Data Index: 376752 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.8669. Min Act: -0.0000

Data Index: 515552 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.9975. Min Act: -0.0000

Data Index: 1359345 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.1298. Min Act: -0.0000

Data Index: 477234 (C4 (Web Text))

Max Activating Token Index: 899