Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1382 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.6923. Min Act: -0.1700

Data Index: 1588351 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.5671. Min Act: -0.1700

Data Index: 1523340 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1423818 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4574. Min Act: -0.1700

Data Index: 1432980 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1602475 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4574. Min Act: -0.1699

Data Index: 1458214 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4417. Min Act: -0.1699

Data Index: 1416000 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1410162 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4260. Min Act: -0.1699

Data Index: 1508825 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1624291 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1621583 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1465273 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1614096 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3947. Min Act: -0.1700

Data Index: 1495045 (Python Code)

Max Activating Token Index: 577

Text #14

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3790. Min Act: -0.1700

Data Index: 1439573 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3790. Min Act: -0.1700

Data Index: 1383681 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3947. Min Act: -0.1700

Data Index: 1507232 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3790. Min Act: -0.1700

Data Index: 1627070 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3633. Min Act: -0.1698

Data Index: 1369645 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 3.6923. Min Range: -3.6923

Max Act: 3.3633. Min Act: -0.1700

Data Index: 1429366 (Python Code)

Max Activating Token Index: 181