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

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

Neuron 1710 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: 3.8785. Min Range: -3.8785

Max Act: 3.8785. Min Act: -0.1700

Data Index: 64085 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.8159. Min Act: -0.1700

Data Index: 166516 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7534. Min Act: -0.1700

Data Index: 189334 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7846. Min Act: -0.1700

Data Index: 973395 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7846. Min Act: -0.1700

Data Index: 1032227 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7534. Min Act: -0.1700

Data Index: 571756 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7534. Min Act: -0.1700

Data Index: 316981 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6908. Min Act: -0.1700

Data Index: 1110373 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.7221. Min Act: -0.1700

Data Index: 897777 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6908. Min Act: -0.1700

Data Index: 819736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6595. Min Act: -0.1700

Data Index: 545140 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6438. Min Act: -0.1700

Data Index: 1218430 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6282. Min Act: -0.1700

Data Index: 446703 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6125. Min Act: -0.1700

Data Index: 1025769 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6438. Min Act: -0.1700

Data Index: 665951 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6282. Min Act: -0.1700

Data Index: 848098 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6438. Min Act: -0.1700

Data Index: 122625 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1008056 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.6125. Min Act: -0.1700

Data Index: 427905 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.8785. Min Range: -3.8785

Max Act: 3.5969. Min Act: -0.1700

Data Index: 703602 (C4 (Web Text))

Max Activating Token Index: 809