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

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

Neuron 1438 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1118. Min Range: -7.1118

Max Act: 7.1118. Min Act: -0.1700

Data Index: 1637086 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.9868. Min Act: -0.1700

Data Index: 1408785 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.8618. Min Act: -0.1700

Data Index: 1604410 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.8618. Min Act: -0.1700

Data Index: 1602316 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.8931. Min Act: -0.1700

Data Index: 1583132 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.8306. Min Act: -0.1700

Data Index: 1543927 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1367688 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.9243. Min Act: -0.1700

Data Index: 1492000 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1638090 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7681. Min Act: -0.1700

Data Index: 1552616 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1529207 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1653631 (Python Code)

Max Activating Token Index: 817

Text #12

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7368. Min Act: -0.1700

Data Index: 1413566 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1559556 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7056. Min Act: -0.1700

Data Index: 1598138 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.8306. Min Act: -0.1700

Data Index: 1552267 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7368. Min Act: -0.1700

Data Index: 1613405 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7993. Min Act: -0.1700

Data Index: 1436776 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7056. Min Act: -0.1700

Data Index: 1481262 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 7.1118. Min Range: -7.1118

Max Act: 6.7368. Min Act: -0.1700

Data Index: 1361095 (Python Code)

Max Activating Token Index: 383