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

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

Neuron 1944 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: 3.4662. Min Range: -3.4662

Max Act: 3.4662. Min Act: -0.1700

Data Index: 113041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3250. Min Act: -0.1700

Data Index: 884505 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1271602 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1192798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2779. Min Act: -0.1700

Data Index: 641476 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2622. Min Act: -0.1700

Data Index: 951994 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2622. Min Act: -0.1700

Data Index: 1011560 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2622. Min Act: -0.1700

Data Index: 796130 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2622. Min Act: -0.1700

Data Index: 501627 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2465. Min Act: -0.1700

Data Index: 1087909 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2307. Min Act: -0.1700

Data Index: 404442 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2307. Min Act: -0.1700

Data Index: 590756 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1023109 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1040114 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2150. Min Act: -0.1700

Data Index: 747110 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2150. Min Act: -0.1700

Data Index: 860393 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1012573 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1993. Min Act: -0.1700

Data Index: 478207 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1993. Min Act: -0.1700

Data Index: 10618 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.2150. Min Act: -0.1700

Data Index: 761863 (C4 (Web Text))

Max Activating Token Index: 1023