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

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

Neuron 1229 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1086681 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2911. Min Act: -0.1700

Data Index: 412489 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2911. Min Act: -0.1700

Data Index: 1133082 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1208179 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2597. Min Act: -0.1700

Data Index: 733067 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2754. Min Act: -0.1700

Data Index: 953271 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1205621 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2754. Min Act: -0.1700

Data Index: 251638 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1003226 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1188283 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1262509 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2440. Min Act: -0.1700

Data Index: 285470 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 624693 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1116818 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2440. Min Act: -0.1700

Data Index: 648261 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 568083 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1085449 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1013510 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2282. Min Act: -0.1700

Data Index: 698698 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.2911. Min Range: -3.2911

Max Act: 3.2125. Min Act: -0.1700

Data Index: 547940 (C4 (Web Text))

Max Activating Token Index: 551