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

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

Neuron 1791 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: 5.3220. Min Range: -5.3220

Max Act: 5.3220. Min Act: -0.1700

Data Index: 709136 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 209663 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.2126. Min Act: -0.1700

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1814. Min Act: -0.1700

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1033. Min Act: -0.1700

Data Index: 882867 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1033. Min Act: -0.1700

Data Index: 675238 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0564. Min Act: -0.1700

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0564. Min Act: -0.1700

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0408. Min Act: -0.1700

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 5.3220. Min Range: -5.3220

Max Act: 4.9939. Min Act: -0.1700

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0876. Min Act: -0.1700

Data Index: 992068 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0095. Min Act: -0.1700

Data Index: 20537 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0251. Min Act: -0.1700

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0095. Min Act: -0.1700

Data Index: 1233114 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0095. Min Act: -0.1699

Data Index: 233702 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 5.3220. Min Range: -5.3220

Max Act: 4.9939. Min Act: -0.1700

Data Index: 503436 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.0095. Min Act: -0.1700

Data Index: 434145 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 5.3220. Min Range: -5.3220

Max Act: 4.9626. Min Act: -0.1700

Data Index: 1070008 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 5.3220. Min Range: -5.3220

Max Act: 4.9939. Min Act: -0.1700

Data Index: 205595 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 5.3220. Min Range: -5.3220

Max Act: 4.9626. Min Act: -0.1700

Data Index: 287749 (C4 (Web Text))

Max Activating Token Index: 559