Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1295 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.9546. Min Act: -0.1700

Data Index: 540913 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.7200. Min Act: -0.1700

Data Index: 609968 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6730. Min Act: -0.1700

Data Index: 917765 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6887. Min Act: -0.1700

Data Index: 727799 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6417. Min Act: -0.1700

Data Index: 1333747 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6417. Min Act: -0.1700

Data Index: 176427 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6261. Min Act: -0.1700

Data Index: 379244 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6417. Min Act: -0.1700

Data Index: 1169909 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.6104. Min Act: -0.1700

Data Index: 405039 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5791. Min Act: -0.1700

Data Index: 1286284 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5321. Min Act: -0.1700

Data Index: 1156590 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5321. Min Act: -0.1700

Data Index: 1126954 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5008. Min Act: -0.1700

Data Index: 511240 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5321. Min Act: -0.1700

Data Index: 79377 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5008. Min Act: -0.1700

Data Index: 637058 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5008. Min Act: -0.1700

Data Index: 1516705 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5321. Min Act: -0.1700

Data Index: 129221 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5165. Min Act: -0.1700

Data Index: 73219 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5321. Min Act: -0.1700

Data Index: 1065975 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 3.9546. Min Range: -3.9546

Max Act: 3.5008. Min Act: -0.1700

Data Index: 150999 (C4 (Web Text))

Max Activating Token Index: 708