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

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

Neuron 1153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0527. Min Act: -0.1700

Data Index: 1424371 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0527. Min Act: -0.1700

Data Index: 1534155 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0370. Min Act: -0.1700

Data Index: 1386691 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0212. Min Act: -0.1700

Data Index: 1609352 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0212. Min Act: -0.1700

Data Index: 1621175 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1606256 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1454842 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1426616 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1401450 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1476315 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1565017 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1435762 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9737. Min Act: -0.1700

Data Index: 1636383 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1610143 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1483862 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9737. Min Act: -0.1700

Data Index: 1445008 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1495214 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9737. Min Act: -0.1700

Data Index: 1564357 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1564404 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1481469 (Python Code)

Max Activating Token Index: 172