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

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

Neuron 927 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: 3.4266. Min Range: -3.4266

Max Act: 3.4266. Min Act: -0.1700

Data Index: 1202269 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3952. Min Act: -0.1700

Data Index: 807573 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3638. Min Act: -0.1700

Data Index: 793285 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3324. Min Act: -0.1700

Data Index: 184271 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3481. Min Act: -0.1700

Data Index: 289046 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3324. Min Act: -0.1700

Data Index: 149793 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3324. Min Act: -0.1700

Data Index: 203987 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3167. Min Act: -0.1700

Data Index: 37839 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3167. Min Act: -0.1700

Data Index: 799250 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3010. Min Act: -0.1700

Data Index: 91375 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3167. Min Act: -0.1700

Data Index: 677448 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3167. Min Act: -0.1700

Data Index: 1231567 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3010. Min Act: -0.1700

Data Index: 670506 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1020955 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2853. Min Act: -0.1700

Data Index: 2092 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2696. Min Act: -0.1700

Data Index: 981418 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2696. Min Act: -0.1700

Data Index: 416819 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1088273 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2696. Min Act: -0.1700

Data Index: 1062788 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2696. Min Act: -0.1700

Data Index: 1001219 (C4 (Web Text))

Max Activating Token Index: 679