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

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

Neuron 221 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.5718. Min Act: -0.1700

Data Index: 871963 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.4155. Min Act: -0.1700

Data Index: 198198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.4468. Min Act: -0.1700

Data Index: 799568 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.2280. Min Act: -0.1700

Data Index: 619661 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.1655. Min Act: -0.1700

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.1030. Min Act: -0.1700

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.1343. Min Act: -0.1700

Data Index: 1438920 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.0718. Min Act: -0.1700

Data Index: 1233895 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.0405. Min Act: -0.1700

Data Index: 342187 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.0718. Min Act: -0.1700

Data Index: 847637 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.0718. Min Act: -0.1700

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 5.5718. Min Range: -5.5718

Max Act: 5.0718. Min Act: -0.1700

Data Index: 1543208 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9780. Min Act: -0.1700

Data Index: 740092 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9155. Min Act: -0.1700

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9468. Min Act: -0.1700

Data Index: 234632 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9468. Min Act: -0.1700

Data Index: 938366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9468. Min Act: -0.1700

Data Index: 891970 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.8843. Min Act: -0.1700

Data Index: 543967 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.9155. Min Act: -0.1700

Data Index: 759787 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 5.5718. Min Range: -5.5718

Max Act: 4.8843. Min Act: -0.1700

Data Index: 19327 (C4 (Web Text))

Max Activating Token Index: 605