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

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

Neuron 829 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.4150. Min Act: -0.1700

Data Index: 119939 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.3525. Min Act: -0.1700

Data Index: 627076 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.3213. Min Act: -0.1700

Data Index: 352762 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.3525. Min Act: -0.1700

Data Index: 994327 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.3213. Min Act: -0.1700

Data Index: 401762 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.2588. Min Act: -0.1699

Data Index: 625105 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.2275. Min Act: -0.1700

Data Index: 494494 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.2275. Min Act: -0.1700

Data Index: 1080254 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1650. Min Act: -0.1700

Data Index: 1110477 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1338. Min Act: -0.1700

Data Index: 607849 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1963. Min Act: -0.1700

Data Index: 1041793 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.2275. Min Act: -0.1700

Data Index: 492917 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1963. Min Act: -0.1700

Data Index: 705221 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1650. Min Act: -0.1700

Data Index: 511674 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1025. Min Act: -0.1700

Data Index: 102974 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1650. Min Act: -0.1700

Data Index: 794147 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1650. Min Act: -0.1700

Data Index: 923635 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1025. Min Act: -0.1700

Data Index: 1101505 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.1025. Min Act: -0.1700

Data Index: 1314022 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 5.4150. Min Range: -5.4150

Max Act: 5.0713. Min Act: -0.1700

Data Index: 313634 (C4 (Web Text))

Max Activating Token Index: 453