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

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

Neuron 770 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.6079. Min Act: -0.1700

Data Index: 1405346 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.5452. Min Act: -0.1700

Data Index: 1577145 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1565355 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1609041 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1452482 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1453102 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1557063 (Python Code)

Max Activating Token Index: 272

Text #7

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1654920 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1623646 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1466120 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1468734 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1619684 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1529015 (Python Code)

Max Activating Token Index: 812

Text #13

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1526624 (Python Code)

Max Activating Token Index: 606

Text #14

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1562187 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1581347 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1517550 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1565506 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1579556 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1483709 (Python Code)

Max Activating Token Index: 140