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

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

Neuron 1913 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1440883 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.2111. Min Act: -0.1700

Data Index: 1542751 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1456486 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1597727 (Python Code)

Max Activating Token Index: 481

Text #4

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1549127 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1375854 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1482. Min Act: -0.1700

Data Index: 1412191 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1324. Min Act: -0.1700

Data Index: 1565671 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1166. Min Act: -0.1700

Data Index: 1444043 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.1009. Min Act: -0.1700

Data Index: 1451151 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1556752 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1575853 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1375765 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1389093 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1361845 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1606967 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1547183 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1372081 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1576710 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 3.3054. Min Range: -3.3054

Max Act: 3.0536. Min Act: -0.1700

Data Index: 1500216 (Python Code)

Max Activating Token Index: 339