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

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

Neuron 501 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: 7.2081. Min Range: -7.2081

Max Act: 7.2081. Min Act: -0.1700

Data Index: 1512874 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.9894. Min Act: -0.1700

Data Index: 1628240 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 7.2081. Min Range: -7.2081

Max Act: 7.0519. Min Act: -0.1700

Data Index: 1565249 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.9581. Min Act: -0.1700

Data Index: 1648239 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.9269. Min Act: -0.1700

Data Index: 1568408 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.9269. Min Act: -0.1700

Data Index: 1515994 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1408936 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1538461 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1550275 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8644. Min Act: -0.1700

Data Index: 1610583 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1416007 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.7706. Min Act: -0.1700

Data Index: 1415796 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8956. Min Act: -0.1700

Data Index: 1470301 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8956. Min Act: -0.1700

Data Index: 1394444 (Python Code)

Max Activating Token Index: 810

Text #14

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8019. Min Act: -0.1700

Data Index: 1584932 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8644. Min Act: -0.1700

Data Index: 1632380 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8019. Min Act: -0.1700

Data Index: 1624505 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1547670 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.7706. Min Act: -0.1700

Data Index: 1564064 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.7706. Min Act: -0.1700

Data Index: 1393149 (Python Code)

Max Activating Token Index: 314