Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1722 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5978. Min Act: -0.1700

Data Index: 646306 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5978. Min Act: -0.1700

Data Index: 290648 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5665. Min Act: -0.1700

Data Index: 319981 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5508. Min Act: -0.1700

Data Index: 1339978 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5195. Min Act: -0.1700

Data Index: 59815 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5195. Min Act: -0.1700

Data Index: 974008 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4881. Min Act: -0.1700

Data Index: 845384 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5195. Min Act: -0.1700

Data Index: 192321 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5195. Min Act: -0.1700

Data Index: 432781 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4725. Min Act: -0.1700

Data Index: 806150 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4881. Min Act: -0.1700

Data Index: 169553 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5038. Min Act: -0.1700

Data Index: 37188 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4881. Min Act: -0.1700

Data Index: 813782 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5038. Min Act: -0.1700

Data Index: 63771 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5038. Min Act: -0.1700

Data Index: 1286760 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5038. Min Act: -0.1700

Data Index: 464478 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.5038. Min Act: -0.1700

Data Index: 548484 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4881. Min Act: -0.1700

Data Index: 765422 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4725. Min Act: -0.1700

Data Index: 886173 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 3.5978. Min Range: -3.5978

Max Act: 3.4725. Min Act: -0.1700

Data Index: 308336 (C4 (Web Text))

Max Activating Token Index: 287