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

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

Neuron 577 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: 3.8242. Min Range: -3.8242

Max Act: 3.8242. Min Act: -0.1700

Data Index: 153765 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7929. Min Act: -0.1700

Data Index: 625400 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7304. Min Act: -0.1700

Data Index: 762734 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7460. Min Act: -0.1700

Data Index: 648103 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7147. Min Act: -0.1700

Data Index: 493974 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7147. Min Act: -0.1700

Data Index: 814570 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6991. Min Act: -0.1700

Data Index: 1238876 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7147. Min Act: -0.1700

Data Index: 512249 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6678. Min Act: -0.1700

Data Index: 917040 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6678. Min Act: -0.1700

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6834. Min Act: -0.1700

Data Index: 1025807 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6834. Min Act: -0.1700

Data Index: 619751 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6834. Min Act: -0.1700

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6834. Min Act: -0.1700

Data Index: 231069 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6834. Min Act: -0.1700

Data Index: 299064 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7147. Min Act: -0.1700

Data Index: 1067811 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6678. Min Act: -0.1700

Data Index: 328388 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6521. Min Act: -0.1700

Data Index: 594493 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6208. Min Act: -0.1700

Data Index: 355486 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6365. Min Act: -0.1700

Data Index: 867121 (C4 (Web Text))

Max Activating Token Index: 273