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

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

Neuron 364 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.4270. Min Act: -0.1700

Data Index: 249186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.3328. Min Act: -0.1700

Data Index: 550768 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1315643 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.2228. Min Act: -0.1700

Data Index: 801600 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1756. Min Act: -0.1700

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1756. Min Act: -0.1700

Data Index: 270538 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1599. Min Act: -0.1700

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1441. Min Act: -0.1700

Data Index: 828541 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1441. Min Act: -0.1700

Data Index: 632697 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1284. Min Act: -0.1700

Data Index: 335325 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1441. Min Act: -0.1700

Data Index: 822232 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1599. Min Act: -0.1700

Data Index: 430708 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1284. Min Act: -0.1700

Data Index: 1218603 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1441. Min Act: -0.1700

Data Index: 1354669 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1441. Min Act: -0.1700

Data Index: 509518 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1284. Min Act: -0.1700

Data Index: 931993 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1126. Min Act: -0.1700

Data Index: 186887 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.0969. Min Act: -0.1700

Data Index: 1155663 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.4270. Min Range: -3.4270

Max Act: 3.1126. Min Act: -0.1700

Data Index: 368383 (C4 (Web Text))

Max Activating Token Index: 377