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

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

Neuron 1349 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: 5.5869. Min Range: -5.5869

Max Act: 5.5869. Min Act: -0.1700

Data Index: 70177 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.5244. Min Act: -0.1700

Data Index: 303061 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.5556. Min Act: -0.1699

Data Index: 181892 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.5244. Min Act: -0.1700

Data Index: 1024014 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.5244. Min Act: -0.1700

Data Index: 192396 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4931. Min Act: -0.1700

Data Index: 822779 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4306. Min Act: -0.1700

Data Index: 227343 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4931. Min Act: -0.1699

Data Index: 252949 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4931. Min Act: -0.1700

Data Index: 1079613 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4931. Min Act: -0.1700

Data Index: 547842 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1700

Data Index: 396120 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4306. Min Act: -0.1700

Data Index: 116057 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4306. Min Act: -0.1699

Data Index: 1061929 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1700

Data Index: 438554 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1700

Data Index: 944863 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1697

Data Index: 1287388 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1700

Data Index: 694754 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.4306. Min Act: -0.1700

Data Index: 764216 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3994. Min Act: -0.1700

Data Index: 392440 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 5.5869. Min Range: -5.5869

Max Act: 5.3681. Min Act: -0.1699

Data Index: 1234780 (C4 (Web Text))

Max Activating Token Index: 268