Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.9314. Min Act: -0.1654

Data Index: 1647148 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.9002. Min Act: -0.0899

Data Index: 1633797 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7752. Min Act: -0.1699

Data Index: 1502472 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.8377. Min Act: -0.1624

Data Index: 1613297 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.8064. Min Act: -0.1699

Data Index: 1575534 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7439. Min Act: -0.1698

Data Index: 1541308 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7752. Min Act: -0.1700

Data Index: 1542477 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6814. Min Act: -0.1699

Data Index: 1425763 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6814. Min Act: -0.0899

Data Index: 1596041 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5877. Min Act: -0.1698

Data Index: 1408128 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6189. Min Act: -0.1645

Data Index: 1506499 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5252. Min Act: -0.1700

Data Index: 1463057 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5877. Min Act: -0.1698

Data Index: 1444933 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5252. Min Act: -0.1547

Data Index: 1501674 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5564. Min Act: -0.1699

Data Index: 1632484 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5252. Min Act: -0.1699

Data Index: 1361271 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.4939. Min Act: -0.1700

Data Index: 1595274 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.4939. Min Act: -0.1688

Data Index: 1449721 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5252. Min Act: -0.1670

Data Index: 1392000 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.5252. Min Act: -0.0899

Data Index: 1444996 (Python Code)

Max Activating Token Index: 506