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

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

Neuron 322 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: 3.2128. Min Range: -3.2128

Max Act: 3.2128. Min Act: -0.1700

Data Index: 1576166 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 3.2128. Min Range: -3.2128

Max Act: 3.1341. Min Act: -0.1700

Data Index: 1387847 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 3.2128. Min Range: -3.2128

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1557619 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 3.2128. Min Range: -3.2128

Max Act: 3.0868. Min Act: -0.1700

Data Index: 1421830 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 3.2128. Min Range: -3.2128

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1396213 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 3.2128. Min Range: -3.2128

Max Act: 3.0395. Min Act: -0.1700

Data Index: 1467354 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9921. Min Act: -0.1700

Data Index: 1427107 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9921. Min Act: -0.1700

Data Index: 1645441 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9604. Min Act: -0.1700

Data Index: 1506441 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1373625 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9604. Min Act: -0.1700

Data Index: 1502749 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9762. Min Act: -0.1700

Data Index: 1391035 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9604. Min Act: -0.1700

Data Index: 1556514 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9287. Min Act: -0.1700

Data Index: 1386726 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9287. Min Act: -0.1700

Data Index: 1449808 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9287. Min Act: -0.1700

Data Index: 1429580 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9129. Min Act: -0.1700

Data Index: 1491125 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9287. Min Act: -0.1700

Data Index: 1400996 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.8812. Min Act: -0.1700

Data Index: 1475779 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 3.2128. Min Range: -3.2128

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1422799 (Python Code)

Max Activating Token Index: 158