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

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

Neuron 866 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: 5.5369. Min Range: -5.5369

Max Act: 5.4432. Min Act: -0.1700

Data Index: 567090 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.5369. Min Act: -0.1700

Data Index: 321082 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.4432. Min Act: -0.1700

Data Index: 500167 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.5057. Min Act: -0.1700

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 782616 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 561166 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 928188 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 1214229 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 76103 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 171509 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3807. Min Act: -0.1700

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 441726 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.2869. Min Act: -0.1700

Data Index: 647070 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 607714 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3182. Min Act: -0.1700

Data Index: 1290268 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3494. Min Act: -0.1700

Data Index: 316269 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 5.5369. Min Range: -5.5369

Max Act: 5.3182. Min Act: -0.1700

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 494