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

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

Neuron 816 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: 3.5594. Min Range: -3.5594

Max Act: 3.5594. Min Act: -0.1700

Data Index: 1541634 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1394389 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1471234 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1504793 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1558985 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1588199 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1456217 (Python Code)

Max Activating Token Index: 291

Text #7

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1414219 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1541988 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1413406 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1572387 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1372094 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1481608 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1444396 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4026. Min Act: -0.1700

Data Index: 1485133 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1427106 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1544370 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1566571 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1466021 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1407855 (Python Code)

Max Activating Token Index: 566