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

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

Neuron 1869 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: 3.6707. Min Range: -3.6707

Max Act: 3.6707. Min Act: -0.1700

Data Index: 83576 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5141. Min Act: -0.1700

Data Index: 1085258 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5141. Min Act: -0.1700

Data Index: 105175 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5454. Min Act: -0.1700

Data Index: 330342 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4827. Min Act: -0.1700

Data Index: 40015 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4514. Min Act: -0.1700

Data Index: 89533 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4514. Min Act: -0.1700

Data Index: 172129 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4827. Min Act: -0.1700

Data Index: 222864 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4200. Min Act: -0.1700

Data Index: 1132886 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4200. Min Act: -0.1700

Data Index: 778075 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 151337 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4200. Min Act: -0.1700

Data Index: 1317940 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 127417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 120438 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 335298 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 202672 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 97217 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 1125113 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 876959 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 142907 (C4 (Web Text))

Max Activating Token Index: 5