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

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

Neuron 1281 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.7105. Min Act: -0.1700

Data Index: 1517276 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.7105. Min Act: -0.1700

Data Index: 1582940 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6479. Min Act: -0.1700

Data Index: 1639154 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6323. Min Act: -0.1700

Data Index: 1375902 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6323. Min Act: -0.1700

Data Index: 1503525 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6323. Min Act: -0.1700

Data Index: 1541036 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6009. Min Act: -0.1700

Data Index: 1487909 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6009. Min Act: -0.1700

Data Index: 1414003 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5853. Min Act: -0.1700

Data Index: 1547447 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1434376 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.6009. Min Act: -0.1700

Data Index: 1552543 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1587859 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1395952 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1376061 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5696. Min Act: -0.1700

Data Index: 1420946 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1598599 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1362683 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5383. Min Act: -0.1700

Data Index: 1530295 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1639884 (Python Code)

Max Activating Token Index: 385

Text #19

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1392786 (Python Code)

Max Activating Token Index: 787