Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1085 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.6709. Min Act: -0.1700

Data Index: 203060 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.6239. Min Act: -0.1700

Data Index: 389982 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.6239. Min Act: -0.1700

Data Index: 253779 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.6083. Min Act: -0.1700

Data Index: 369252 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5926. Min Act: -0.1700

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5770. Min Act: -0.1700

Data Index: 453087 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5770. Min Act: -0.1700

Data Index: 356621 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.6083. Min Act: -0.1700

Data Index: 392505 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5926. Min Act: -0.1700

Data Index: 161794 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5770. Min Act: -0.1700

Data Index: 1349147 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5770. Min Act: -0.1700

Data Index: 633601 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5926. Min Act: -0.1700

Data Index: 956818 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5456. Min Act: -0.1700

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5300. Min Act: -0.1700

Data Index: 25096 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5300. Min Act: -0.1700

Data Index: 1045969 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5456. Min Act: -0.1700

Data Index: 981711 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5456. Min Act: -0.1700

Data Index: 36434 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.5456. Min Act: -0.1700

Data Index: 237704 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1240247 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 3.6709. Min Range: -3.6709

Max Act: 3.4203. Min Act: -0.1700

Data Index: 976295 (C4 (Web Text))

Max Activating Token Index: 948