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

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

Neuron 1202 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: 5.9063. Min Range: -5.9063

Max Act: 5.9063. Min Act: -0.1700

Data Index: 511911 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.7813. Min Act: -0.1700

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.8125. Min Act: -0.1700

Data Index: 1173999 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.7813. Min Act: -0.1700

Data Index: 1164741 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.6563. Min Act: -0.1700

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.6250. Min Act: -0.1700

Data Index: 588453 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.6563. Min Act: -0.1700

Data Index: 673587 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5938. Min Act: -0.1700

Data Index: 1205038 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5938. Min Act: -0.1700

Data Index: 618264 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5625. Min Act: -0.1700

Data Index: 176520 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5625. Min Act: -0.1700

Data Index: 600298 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5938. Min Act: -0.1700

Data Index: 788716 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5625. Min Act: -0.1700

Data Index: 469750 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5313. Min Act: -0.1700

Data Index: 248889 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5313. Min Act: -0.1700

Data Index: 950909 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5313. Min Act: -0.1700

Data Index: 1203348 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5625. Min Act: -0.1700

Data Index: 318982 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5313. Min Act: -0.1700

Data Index: 820754 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5313. Min Act: -0.1700

Data Index: 126768 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 5.9063. Min Range: -5.9063

Max Act: 5.5000. Min Act: -0.1700

Data Index: 1154487 (C4 (Web Text))

Max Activating Token Index: 737