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

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

Neuron 1006 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: 3.6797. Min Range: -3.6797

Max Act: 3.6797. Min Act: -0.1680

Data Index: 460946 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6641. Min Act: -0.1649

Data Index: 58388 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6484. Min Act: -0.1699

Data Index: 824084 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6641. Min Act: -0.1679

Data Index: 390858 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6641. Min Act: -0.1675

Data Index: 107270 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6641. Min Act: -0.1699

Data Index: 574077 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6484. Min Act: -0.1692

Data Index: 368203 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6328. Min Act: -0.1677

Data Index: 733954 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6171. Min Act: -0.1700

Data Index: 330519 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6328. Min Act: -0.1698

Data Index: 1055282 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6171. Min Act: -0.1700

Data Index: 1161251 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5701. Min Act: -0.1694

Data Index: 159547 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1699

Data Index: 1211540 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5858. Min Act: -0.1700

Data Index: 1268877 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5701. Min Act: -0.1621

Data Index: 1204149 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5701. Min Act: -0.1699

Data Index: 574724 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1699

Data Index: 448166 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5701. Min Act: -0.1699

Data Index: 168189 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5545. Min Act: -0.1700

Data Index: 886299 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5701. Min Act: -0.1700

Data Index: 650140 (C4 (Web Text))

Max Activating Token Index: 861