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

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

Neuron 220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1468706 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.3724. Min Act: -0.1700

Data Index: 1449973 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.3724. Min Act: -0.1700

Data Index: 1468592 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1390294 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.1838. Min Act: -0.1700

Data Index: 1617471 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.1366. Min Act: -0.1700

Data Index: 1586747 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.1208. Min Act: -0.1700

Data Index: 1376744 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1626201 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1614069 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1428123 (Python Code)

Max Activating Token Index: 227

Text #10

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1600296 (Python Code)

Max Activating Token Index: 917

Text #11

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0577. Min Act: -0.1700

Data Index: 1441858 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0104. Min Act: -0.1700

Data Index: 1596695 (Python Code)

Max Activating Token Index: 830

Text #13

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0262. Min Act: -0.1700

Data Index: 1618009 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0262. Min Act: -0.1700

Data Index: 1406706 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0104. Min Act: -0.1700

Data Index: 1593528 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0262. Min Act: -0.1700

Data Index: 1492678 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0419. Min Act: -0.1700

Data Index: 1409047 (Python Code)

Max Activating Token Index: 717

Text #18

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0104. Min Act: -0.1700

Data Index: 1615239 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 3.3880. Min Range: -3.3880

Max Act: 3.0104. Min Act: -0.1700

Data Index: 1476336 (Python Code)

Max Activating Token Index: 254