Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.6742. Min Act: -0.1700

Data Index: 2168704 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.6974. Min Act: -0.1700

Data Index: 32572 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.7037. Min Act: -0.1700

Data Index: 1934273 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.7077. Min Act: -0.1700

Data Index: 5861289 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1634396 (Open Web Text)

Max Activating Token Index: 867

Text #5

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5752. Min Act: -0.1700

Data Index: 948077 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5771. Min Act: -0.1700

Data Index: 1656170 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.6468. Min Act: -0.1700

Data Index: 3076678 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.6093. Min Act: -0.1700

Data Index: 2191169 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5861. Min Act: -0.1700

Data Index: 3964472 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5926. Min Act: -0.1700

Data Index: 5370456 (Open Web Text)

Max Activating Token Index: 1008

Text #11

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5899. Min Act: -0.1700

Data Index: 6926974 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5816. Min Act: -0.1700

Data Index: 6946322 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5610. Min Act: -0.1700

Data Index: 3628473 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5823. Min Act: -0.1700

Data Index: 4043424 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1649321 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5867. Min Act: -0.1700

Data Index: 4312128 (Open Web Text)

Max Activating Token Index: 815

Text #17

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5411. Min Act: -0.1700

Data Index: 4480784 (Open Web Text)

Max Activating Token Index: 860

Text #18

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1928772 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 3.7077. Min Range: -3.7077

Max Act: 3.5774. Min Act: -0.1700

Data Index: 1002231 (Open Web Text)

Max Activating Token Index: 417