Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1537 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.3144. Min Act: -0.1698

Data Index: 1538740 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.2519. Min Act: -0.1700

Data Index: 1391490 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.1894. Min Act: -0.1700

Data Index: 1559534 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.2207. Min Act: -0.1699

Data Index: 1476729 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.1582. Min Act: -0.1700

Data Index: 1462999 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.1269. Min Act: -0.1700

Data Index: 1522770 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.0956. Min Act: -0.1700

Data Index: 1656067 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.0331. Min Act: -0.1700

Data Index: 1374170 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 4.3144. Min Range: -4.3144

Max Act: 4.0018. Min Act: -0.1700

Data Index: 1461357 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.8768. Min Act: -0.1700

Data Index: 1562762 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9393. Min Act: -0.1700

Data Index: 1539818 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9706. Min Act: -0.1699

Data Index: 1456262 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9080. Min Act: -0.1699

Data Index: 1459979 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9706. Min Act: -0.1700

Data Index: 1420005 (Python Code)

Max Activating Token Index: 1016

Text #14

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9393. Min Act: -0.1700

Data Index: 1519408 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9080. Min Act: -0.1700

Data Index: 1419068 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9080. Min Act: -0.1700

Data Index: 1421331 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9706. Min Act: -0.1700

Data Index: 1581027 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.9080. Min Act: -0.1700

Data Index: 1600178 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 4.3144. Min Range: -4.3144

Max Act: 3.8768. Min Act: -0.1700

Data Index: 1642217 (Python Code)

Max Activating Token Index: 394