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

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

Neuron 498 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: 5.5440. Min Range: -5.5440

Max Act: 5.5128. Min Act: -0.1700

Data Index: 680909 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.5440. Min Act: -0.1700

Data Index: 711046 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.4503. Min Act: -0.1700

Data Index: 202460 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.4503. Min Act: -0.1700

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.4815. Min Act: -0.1700

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 1184753 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3878. Min Act: -0.1700

Data Index: 1162178 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 1236087 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 49712 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 966240 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 379741 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3253. Min Act: -0.1700

Data Index: 1066461 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3253. Min Act: -0.1700

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3253. Min Act: -0.1700

Data Index: 879166 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.2940. Min Act: -0.1700

Data Index: 324101 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.2628. Min Act: -0.1700

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.2628. Min Act: -0.1700

Data Index: 1155140 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3565. Min Act: -0.1700

Data Index: 734289 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.2940. Min Act: -0.1700

Data Index: 766576 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 5.5440. Min Range: -5.5440

Max Act: 5.3253. Min Act: -0.1700

Data Index: 496237 (C4 (Web Text))

Max Activating Token Index: 129