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

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

Neuron 254 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: 3.1870. Min Range: -3.1870

Max Act: 3.1555. Min Act: -0.1700

Data Index: 118557 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1870. Min Act: -0.1700

Data Index: 55097 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1555. Min Act: -0.1700

Data Index: 256017 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1124267 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1352861 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0925. Min Act: -0.1700

Data Index: 309314 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1240. Min Act: -0.1700

Data Index: 925401 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0925. Min Act: -0.1700

Data Index: 418097 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1240. Min Act: -0.1700

Data Index: 830255 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0925. Min Act: -0.1700

Data Index: 232228 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1555. Min Act: -0.1700

Data Index: 960331 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1240. Min Act: -0.1700

Data Index: 199921 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0767. Min Act: -0.1700

Data Index: 808180 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0767. Min Act: -0.1700

Data Index: 1302753 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0925. Min Act: -0.1700

Data Index: 323080 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0609. Min Act: -0.1700

Data Index: 673738 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0767. Min Act: -0.1700

Data Index: 424049 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0767. Min Act: -0.1700

Data Index: 697 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0452. Min Act: -0.1700

Data Index: 880483 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0452. Min Act: -0.1700

Data Index: 422013 (C4 (Web Text))

Max Activating Token Index: 194