Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 704 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.7978. Min Act: -0.1700

Data Index: 492121 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.7208. Min Act: -0.1700

Data Index: 797757 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.6609. Min Act: -0.1700

Data Index: 1040099 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.6031. Min Act: -0.1700

Data Index: 651045 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.6129. Min Act: -0.1700

Data Index: 357011 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5718. Min Act: -0.1700

Data Index: 699396 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5505. Min Act: -0.1700

Data Index: 42115 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5594. Min Act: -0.1700

Data Index: 560302 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5358. Min Act: -0.1700

Data Index: 1062217 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5309. Min Act: -0.1700

Data Index: 855830 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5008. Min Act: -0.1700

Data Index: 1134295 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5125. Min Act: -0.1700

Data Index: 1259015 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5012. Min Act: -0.1700

Data Index: 241156 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5259. Min Act: -0.1700

Data Index: 889020 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.4667. Min Act: -0.1700

Data Index: 1124736 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.4960. Min Act: -0.1700

Data Index: 904818 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.5102. Min Act: -0.1700

Data Index: 349394 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.4851. Min Act: -0.1700

Data Index: 815287 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.4725. Min Act: -0.1700

Data Index: 952515 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 4.7978. Min Range: -4.7978

Max Act: 4.4793. Min Act: -0.1700

Data Index: 1140820 (C4 (Web Text))

Max Activating Token Index: 458