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

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

Neuron 1458 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.2353. Min Act: -0.1700

Data Index: 957715 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.1566. Min Act: -0.1700

Data Index: 876174 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.1409. Min Act: -0.1700

Data Index: 739524 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.1251. Min Act: -0.1700

Data Index: 154815 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.1094. Min Act: -0.1700

Data Index: 870133 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 594114 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 904922 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 744873 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 358543 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 986441 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 649671 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0936. Min Act: -0.1700

Data Index: 865093 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 709012 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 116263 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 1137077 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 1196238 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.1094. Min Act: -0.1700

Data Index: 8731 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 1210633 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 144757 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.2353. Min Range: -3.2353

Max Act: 3.0778. Min Act: -0.1700

Data Index: 1246984 (C4 (Web Text))

Max Activating Token Index: 18