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

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

Neuron 859 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: 3.6035. Min Range: -3.6035

Max Act: 3.6035. Min Act: -0.1700

Data Index: 815050 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5409. Min Act: -0.1700

Data Index: 62223 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5722. Min Act: -0.1700

Data Index: 880329 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.6035. Min Act: -0.1700

Data Index: 836359 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5409. Min Act: -0.1700

Data Index: 1179163 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5096. Min Act: -0.1700

Data Index: 303744 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4469. Min Act: -0.1700

Data Index: 602076 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4155. Min Act: -0.1700

Data Index: 866072 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4155. Min Act: -0.1700

Data Index: 816501 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4155. Min Act: -0.1700

Data Index: 653018 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4155. Min Act: -0.1700

Data Index: 862940 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3842. Min Act: -0.1700

Data Index: 1225860 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3528. Min Act: -0.1700

Data Index: 41024 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3842. Min Act: -0.1700

Data Index: 817907 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3842. Min Act: -0.1700

Data Index: 118032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1282638 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3842. Min Act: -0.1700

Data Index: 1118790 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4155. Min Act: -0.1700

Data Index: 948081 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3528. Min Act: -0.1700

Data Index: 531991 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.3842. Min Act: -0.1700

Data Index: 539881 (C4 (Web Text))

Max Activating Token Index: 396