Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 183 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.7109. Min Act: -0.1700

Data Index: 776812 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6327. Min Act: -0.1700

Data Index: 981888 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6327. Min Act: -0.1700

Data Index: 515907 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6170. Min Act: -0.1700

Data Index: 98113 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6327. Min Act: -0.1700

Data Index: 594554 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6014. Min Act: -0.1700

Data Index: 663709 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6327. Min Act: -0.1700

Data Index: 415748 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5857. Min Act: -0.1700

Data Index: 1240353 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5857. Min Act: -0.1700

Data Index: 540723 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.6170. Min Act: -0.1700

Data Index: 91394 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5544. Min Act: -0.1700

Data Index: 819757 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5700. Min Act: -0.1700

Data Index: 316667 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5857. Min Act: -0.1700

Data Index: 861920 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5857. Min Act: -0.1700

Data Index: 1289739 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5700. Min Act: -0.1700

Data Index: 191064 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1229501 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5230. Min Act: -0.1700

Data Index: 852934 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5074. Min Act: -0.1700

Data Index: 787271 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.4917. Min Act: -0.1700

Data Index: 1232245 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.7109. Min Range: -3.7109

Max Act: 3.5387. Min Act: -0.1700

Data Index: 855402 (C4 (Web Text))

Max Activating Token Index: 690