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

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

Neuron 1385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.8039. Min Act: -0.1700

Data Index: 28810 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.8352. Min Act: -0.1700

Data Index: 23486 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.7727. Min Act: -0.1700

Data Index: 121588 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.6789. Min Act: -0.1700

Data Index: 611937 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.6789. Min Act: -0.1700

Data Index: 403424 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5852. Min Act: -0.1700

Data Index: 777999 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5852. Min Act: -0.1700

Data Index: 698584 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5539. Min Act: -0.1700

Data Index: 925951 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.6477. Min Act: -0.1700

Data Index: 893199 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5852. Min Act: -0.1700

Data Index: 1151007 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5852. Min Act: -0.1700

Data Index: 174890 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.4914. Min Act: -0.1700

Data Index: 142681 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5539. Min Act: -0.1700

Data Index: 1004198 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5852. Min Act: -0.1700

Data Index: 1140797 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5227. Min Act: -0.1700

Data Index: 1286754 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.4914. Min Act: -0.1700

Data Index: 1255449 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5227. Min Act: -0.1700

Data Index: 1022807 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5539. Min Act: -0.1700

Data Index: 1175342 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.5227. Min Act: -0.1700

Data Index: 728075 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 5.8352. Min Range: -5.8352

Max Act: 5.4914. Min Act: -0.1700

Data Index: 1170236 (C4 (Web Text))

Max Activating Token Index: 191