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

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

Neuron 2456 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: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1602598 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1506318 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1521198 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1607266 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1443822 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1623922 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1484275 (Python Code)

Max Activating Token Index: 517

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1461318 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1434014 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1508838 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1582470 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1466854 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1588448 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1561322 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1535269 (Python Code)

Max Activating Token Index: 266

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1560504 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1375145 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1531598 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1589085 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1540759 (Python Code)

Max Activating Token Index: 188