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

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

Neuron 251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4864. Min Act: -0.1700

Data Index: 1001884 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4551. Min Act: -0.1700

Data Index: 607851 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4081. Min Act: -0.1700

Data Index: 825444 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4394. Min Act: -0.1700

Data Index: 878661 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4081. Min Act: -0.1700

Data Index: 455971 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4237. Min Act: -0.1700

Data Index: 1245570 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4394. Min Act: -0.1700

Data Index: 1203725 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3924. Min Act: -0.1700

Data Index: 296826 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4081. Min Act: -0.1700

Data Index: 175588 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3610. Min Act: -0.1700

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3296. Min Act: -0.1700

Data Index: 795516 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3767. Min Act: -0.1700

Data Index: 543587 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3453. Min Act: -0.1700

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3296. Min Act: -0.1700

Data Index: 233290 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3453. Min Act: -0.1700

Data Index: 1309781 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3767. Min Act: -0.1700

Data Index: 78831 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3924. Min Act: -0.1700

Data Index: 762734 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3610. Min Act: -0.1700

Data Index: 299787 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3139. Min Act: -0.1700

Data Index: 1124788 (C4 (Web Text))

Max Activating Token Index: 614