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

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

Neuron 2208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0001

Data Index: 645221 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0542. Min Act: -0.0001

Data Index: 140202 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0462. Min Act: -0.0001

Data Index: 480152 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1245494 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0490. Min Act: -0.0001

Data Index: 609917 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1454150 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1173730 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0480. Min Act: -0.0001

Data Index: 989503 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0463. Min Act: -0.0001

Data Index: 456764 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0461. Min Act: -0.0001

Data Index: 695756 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1309504 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0418. Min Act: -0.0001

Data Index: 299877 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0445. Min Act: -0.0001

Data Index: 614827 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0426. Min Act: -0.0001

Data Index: 722810 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0434. Min Act: -0.0001

Data Index: 208549 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0378. Min Act: -0.0001

Data Index: 12635 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0430. Min Act: -0.0001

Data Index: 676238 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1306059 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0398. Min Act: -0.0001

Data Index: 934537 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1277908 (C4 (Web Text))

Max Activating Token Index: 538