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

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

Neuron 385 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: 5.3015. Min Range: -5.3015

Max Act: 5.3015. Min Act: -0.1700

Data Index: 1479664 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.2703. Min Act: -0.1700

Data Index: 1526779 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.1453. Min Act: -0.1700

Data Index: 1405403 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.1453. Min Act: -0.1700

Data Index: 1545356 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.0828. Min Act: -0.1700

Data Index: 1536907 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.0828. Min Act: -0.1700

Data Index: 1582217 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.1140. Min Act: -0.1700

Data Index: 1478842 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.0515. Min Act: -0.1700

Data Index: 1620880 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.0203. Min Act: -0.1700

Data Index: 1399285 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1564594 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1431534 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1568863 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1386511 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 5.3015. Min Range: -5.3015

Max Act: 5.0203. Min Act: -0.1700

Data Index: 1245609 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1635380 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1605401 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1528514 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1419221 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9578. Min Act: -0.1700

Data Index: 1494049 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 5.3015. Min Range: -5.3015

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1607168 (Python Code)

Max Activating Token Index: 1005