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

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

Neuron 830 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: 3.7256. Min Range: -3.7256

Max Act: 3.7256. Min Act: -0.1700

Data Index: 890680 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.7256. Min Act: -0.1700

Data Index: 1383968 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1656212 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1613725 (Python Code)

Max Activating Token Index: 142

Text #4

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1438664 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1623661 (Python Code)

Max Activating Token Index: 321

Text #6

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5691. Min Act: -0.1700

Data Index: 226380 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1586296 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.6004. Min Act: -0.1700

Data Index: 1599322 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5691. Min Act: -0.1700

Data Index: 1375730 (Python Code)

Max Activating Token Index: 923

Text #10

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5377. Min Act: -0.1700

Data Index: 1415304 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5691. Min Act: -0.1700

Data Index: 1371573 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5377. Min Act: -0.1700

Data Index: 1475118 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1530863 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1359849 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1485236 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1544331 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5377. Min Act: -0.1700

Data Index: 1391594 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1404073 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 3.7256. Min Range: -3.7256

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1523369 (Python Code)

Max Activating Token Index: 180