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

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

Neuron 277 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: 3.8076. Min Range: -3.8076

Max Act: 3.8076. Min Act: -0.1700

Data Index: 587622 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.7137. Min Act: -0.1700

Data Index: 1380851 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.7606. Min Act: -0.1700

Data Index: 1467250 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.7137. Min Act: -0.1700

Data Index: 1580373 (Python Code)

Max Activating Token Index: 488

Text #4

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1606444 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6981. Min Act: -0.1700

Data Index: 1457055 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6824. Min Act: -0.1700

Data Index: 1518009 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6981. Min Act: -0.1700

Data Index: 1084318 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6824. Min Act: -0.1700

Data Index: 1552740 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1480251 (Python Code)

Max Activating Token Index: 234

Text #10

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6668. Min Act: -0.1700

Data Index: 1623008 (Python Code)

Max Activating Token Index: 647

Text #11

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1440146 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1407208 (Python Code)

Max Activating Token Index: 843

Text #13

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1427297 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1625940 (Python Code)

Max Activating Token Index: 936

Text #15

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1606169 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1374740 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1572876 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1542462 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 3.8076. Min Range: -3.8076

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1573904 (Python Code)

Max Activating Token Index: 385