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

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

Neuron 721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.4796. Min Act: -0.1700

Data Index: 1192116 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.4014. Min Act: -0.1700

Data Index: 941884 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.2452. Min Act: -0.1700

Data Index: 647920 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.2764. Min Act: -0.1700

Data Index: 12667 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.1514. Min Act: -0.1700

Data Index: 321391 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.0889. Min Act: -0.1700

Data Index: 441897 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.0421. Min Act: -0.1700

Data Index: 286564 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 5.4796. Min Range: -5.4796

Max Act: 5.0577. Min Act: -0.1700

Data Index: 330425 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9796. Min Act: -0.1700

Data Index: 1093999 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9014. Min Act: -0.1700

Data Index: 721371 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9014. Min Act: -0.1700

Data Index: 1124507 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9014. Min Act: -0.1700

Data Index: 1265638 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9171. Min Act: -0.1700

Data Index: 1160235 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.8389. Min Act: -0.1700

Data Index: 253408 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.9327. Min Act: -0.1700

Data Index: 275882 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.8702. Min Act: -0.1700

Data Index: 879854 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.7452. Min Act: -0.1700

Data Index: 915585 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.8233. Min Act: -0.1700

Data Index: 1262941 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.8702. Min Act: -0.1700

Data Index: 1093011 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 5.4796. Min Range: -5.4796

Max Act: 4.8546. Min Act: -0.1700

Data Index: 148577 (C4 (Web Text))

Max Activating Token Index: 784