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

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

Neuron 1360 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0356. Min Range: -3.0356

Max Act: 3.0356. Min Act: -0.1700

Data Index: 1023190 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 3.0356. Min Range: -3.0356

Max Act: 3.0040. Min Act: -0.1700

Data Index: 1082624 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.9724. Min Act: -0.1700

Data Index: 1180513 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.9407. Min Act: -0.1700

Data Index: 1256129 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.9090. Min Act: -0.1700

Data Index: 1093755 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.9090. Min Act: -0.1700

Data Index: 1279598 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8931. Min Act: -0.1700

Data Index: 69498 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8614. Min Act: -0.1700

Data Index: 1248640 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8773. Min Act: -0.1700

Data Index: 122139 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8614. Min Act: -0.1700

Data Index: 882722 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8931. Min Act: -0.1700

Data Index: 208069 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8773. Min Act: -0.1700

Data Index: 643404 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8614. Min Act: -0.1700

Data Index: 931654 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8614. Min Act: -0.1700

Data Index: 1054722 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8773. Min Act: -0.1700

Data Index: 664716 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8773. Min Act: -0.1700

Data Index: 334057 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8455. Min Act: -0.1700

Data Index: 924348 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8455. Min Act: -0.1700

Data Index: 981688 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8455. Min Act: -0.1700

Data Index: 701299 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 3.0356. Min Range: -3.0356

Max Act: 2.8455. Min Act: -0.1700

Data Index: 5437 (C4 (Web Text))

Max Activating Token Index: 927