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

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

Neuron 5147 in Layer 0

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: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1154380 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0492. Min Act: -0.0001

Data Index: 925098 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0484. Min Act: -0.0001

Data Index: 392107 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1405419 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1057128 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0460. Min Act: -0.0001

Data Index: 688393 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0459. Min Act: -0.0001

Data Index: 914475 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0442. Min Act: -0.0002

Data Index: 410356 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1490906 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1568486 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1146056 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0426. Min Act: -0.0001

Data Index: 288615 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0420. Min Act: -0.0001

Data Index: 293896 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0425. Min Act: -0.0001

Data Index: 379189 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0412. Min Act: -0.0001

Data Index: 789480 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0413. Min Act: -0.0001

Data Index: 973773 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0406. Min Act: -0.0001

Data Index: 166758 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1554001 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1483211 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0400. Min Act: -0.0001

Data Index: 534900 (C4 (Web Text))

Max Activating Token Index: 493