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

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

Neuron 833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.9300. Min Act: -0.1700

Data Index: 112960 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.8362. Min Act: -0.1700

Data Index: 763751 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.8049. Min Act: -0.1700

Data Index: 212446 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.8362. Min Act: -0.1700

Data Index: 986642 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7736. Min Act: -0.1700

Data Index: 557699 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7736. Min Act: -0.1700

Data Index: 872373 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.8049. Min Act: -0.1700

Data Index: 490826 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7423. Min Act: -0.1700

Data Index: 1330666 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7423. Min Act: -0.1700

Data Index: 390023 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7736. Min Act: -0.1700

Data Index: 1309827 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7423. Min Act: -0.1700

Data Index: 551824 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 792788 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 478194 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 289867 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 629534 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 541473 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.6484. Min Act: -0.1700

Data Index: 1280379 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 1278185 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.7110. Min Act: -0.1700

Data Index: 611161 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.9300. Min Range: -3.9300

Max Act: 3.6797. Min Act: -0.1700

Data Index: 322552 (C4 (Web Text))

Max Activating Token Index: 132