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

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

Neuron 575 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: 3.5083. Min Range: -3.5083

Max Act: 3.4926. Min Act: -0.1700

Data Index: 782373 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4770. Min Act: -0.1700

Data Index: 652535 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.5083. Min Act: -0.1700

Data Index: 467037 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1059704 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4613. Min Act: -0.1700

Data Index: 512043 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 1165558 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4456. Min Act: -0.1700

Data Index: 563329 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 651254 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 248798 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 898943 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 236520 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4456. Min Act: -0.1700

Data Index: 548085 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 1344453 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.3986. Min Act: -0.1700

Data Index: 428203 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4299. Min Act: -0.1700

Data Index: 563493 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.4142. Min Act: -0.1700

Data Index: 957291 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.3986. Min Act: -0.1700

Data Index: 812730 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.3829. Min Act: -0.1700

Data Index: 1034332 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.3829. Min Act: -0.1700

Data Index: 791636 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.3829. Min Act: -0.1700

Data Index: 671666 (C4 (Web Text))

Max Activating Token Index: 222