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

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

Neuron 232 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: 5.1693. Min Range: -5.1693

Max Act: 5.1693. Min Act: -0.1700

Data Index: 684269 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.1381. Min Act: -0.1700

Data Index: 346828 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0756. Min Act: -0.1700

Data Index: 284687 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0443. Min Act: -0.1700

Data Index: 386552 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0131. Min Act: -0.1700

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0756. Min Act: -0.1700

Data Index: 258326 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 833839 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0443. Min Act: -0.1700

Data Index: 481668 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0131. Min Act: -0.1700

Data Index: 532309 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0131. Min Act: -0.1700

Data Index: 1187059 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 5.1693. Min Range: -5.1693

Max Act: 5.0131. Min Act: -0.1700

Data Index: 1141051 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 580128 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 1132219 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 784601 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9506. Min Act: -0.1700

Data Index: 192614 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9506. Min Act: -0.1700

Data Index: 172845 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9506. Min Act: -0.1700

Data Index: 297176 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 5.1693. Min Range: -5.1693

Max Act: 4.9818. Min Act: -0.1700

Data Index: 193961 (C4 (Web Text))

Max Activating Token Index: 787