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

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

Neuron 846 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: 3.9474. Min Range: -3.9474

Max Act: 3.9474. Min Act: -0.1700

Data Index: 893726 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1036918 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.8536. Min Act: -0.1700

Data Index: 1151230 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7910. Min Act: -0.1700

Data Index: 338750 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1156942 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7910. Min Act: -0.1700

Data Index: 432794 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.8223. Min Act: -0.1700

Data Index: 538176 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 1342182 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7910. Min Act: -0.1700

Data Index: 1172166 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7598. Min Act: -0.1700

Data Index: 576372 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 973796 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 1207349 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 711689 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 1355952 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 1057151 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.6972. Min Act: -0.1700

Data Index: 62947 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.7285. Min Act: -0.1700

Data Index: 602958 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.6972. Min Act: -0.1700

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.6972. Min Act: -0.1700

Data Index: 1024659 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.9474. Min Range: -3.9474

Max Act: 3.6972. Min Act: -0.1700

Data Index: 1202019 (C4 (Web Text))

Max Activating Token Index: 257