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

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

Neuron 1632 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.6289. Min Act: -0.0002

Data Index: 228658 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.3941. Min Act: -0.0003

Data Index: 545270 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.3316. Min Act: -0.0002

Data Index: 813096 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.3811. Min Act: -0.0002

Data Index: 1336687 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.2569. Min Act: -0.0002

Data Index: 425239 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.1966. Min Act: -0.0003

Data Index: 51063 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.1441. Min Act: -0.0002

Data Index: 311208 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.1301. Min Act: -0.0002

Data Index: 1136676 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.0446. Min Act: -0.0002

Data Index: 1015446 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.0510. Min Act: -0.0002

Data Index: 1166013 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9760. Min Act: -0.0002

Data Index: 1303883 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9469. Min Act: -0.0002

Data Index: 422841 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9805. Min Act: -0.0002

Data Index: 185215 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9247. Min Act: -0.0002

Data Index: 844246 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9212. Min Act: -0.0002

Data Index: 407949 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9076. Min Act: -0.0002

Data Index: 408070 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.9152. Min Act: -0.0002

Data Index: 1042709 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.8721. Min Act: -0.0002

Data Index: 1049808 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.8758. Min Act: -0.0003

Data Index: 826046 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.6289. Min Range: -2.6289

Max Act: 1.8575. Min Act: -0.0002

Data Index: 1034060 (C4 (Web Text))

Max Activating Token Index: 429