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

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

Neuron 854 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: 5.8139. Min Range: -5.8139

Max Act: 5.8139. Min Act: -0.1700

Data Index: 1252947 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.5014. Min Act: -0.1700

Data Index: 872144 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.5014. Min Act: -0.1700

Data Index: 597 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.3452. Min Act: -0.1700

Data Index: 250851 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2827. Min Act: -0.1700

Data Index: 17751 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 434409 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2827. Min Act: -0.1700

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2827. Min Act: -0.1700

Data Index: 299903 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 275865 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2827. Min Act: -0.1700

Data Index: 1129035 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 369106 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 1212013 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 866942 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2202. Min Act: -0.1700

Data Index: 368711 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 1005567 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.1264. Min Act: -0.1700

Data Index: 706371 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2202. Min Act: -0.1700

Data Index: 279608 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2202. Min Act: -0.1700

Data Index: 892918 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.2514. Min Act: -0.1700

Data Index: 469560 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 5.8139. Min Range: -5.8139

Max Act: 5.1889. Min Act: -0.1700

Data Index: 184450 (C4 (Web Text))

Max Activating Token Index: 911