Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1913 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.2483. Min Act: -0.0001

Data Index: 485675 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.2656. Min Act: -0.0001

Data Index: 820303 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1486. Min Act: -0.0001

Data Index: 39358 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1372. Min Act: -0.0001

Data Index: 1143857 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0588. Min Act: -0.0001

Data Index: 247615 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0527. Min Act: -0.0001

Data Index: 1062242 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0739. Min Act: -0.0001

Data Index: 628440 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1024. Min Act: -0.0001

Data Index: 325749 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0267. Min Act: -0.0001

Data Index: 584306 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8962. Min Act: -0.0001

Data Index: 862926 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9698. Min Act: -0.0001

Data Index: 397707 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9399. Min Act: -0.0001

Data Index: 202236 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9163. Min Act: -0.0001

Data Index: 102753 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9400. Min Act: -0.0001

Data Index: 1271927 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9580. Min Act: -0.0001

Data Index: 303463 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9495. Min Act: -0.0001

Data Index: 18330 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8534. Min Act: -0.0001

Data Index: 1064184 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9103. Min Act: -0.0001

Data Index: 1299666 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8550. Min Act: -0.0001

Data Index: 587756 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9391. Min Act: -0.0001

Data Index: 442689 (C4 (Web Text))

Max Activating Token Index: 228