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

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

Neuron 1790 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.7621. Min Act: -0.1700

Data Index: 734519 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.6996. Min Act: -0.1700

Data Index: 963417 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.6371. Min Act: -0.1700

Data Index: 687915 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 601380 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 225308 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5746. Min Act: -0.1699

Data Index: 59142 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5746. Min Act: -0.1700

Data Index: 1160495 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 999247 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 80558 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 598316 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5434. Min Act: -0.1700

Data Index: 584484 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5746. Min Act: -0.1700

Data Index: 324143 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.5121. Min Act: -0.1700

Data Index: 889071 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4809. Min Act: -0.1699

Data Index: 1191201 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4809. Min Act: -0.1700

Data Index: 90941 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4496. Min Act: -0.1700

Data Index: 11501 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4184. Min Act: -0.1700

Data Index: 506434 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4809. Min Act: -0.1700

Data Index: 297258 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.3871. Min Act: -0.1700

Data Index: 457224 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 5.7621. Min Range: -5.7621

Max Act: 5.4496. Min Act: -0.1700

Data Index: 253565 (C4 (Web Text))

Max Activating Token Index: 723