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

Dataset: Open Web Text

Neuron 771 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: 3.2967. Min Range: -3.2967

Max Act: 3.2967. Min Act: -0.1700

Data Index: 6816740 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.2121. Min Act: -0.1700

Data Index: 2339360 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1822. Min Act: -0.1700

Data Index: 6838995 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1715. Min Act: -0.1700

Data Index: 4571112 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1430. Min Act: -0.1700

Data Index: 5159698 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1420. Min Act: -0.1700

Data Index: 3400183 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1518. Min Act: -0.1700

Data Index: 8039130 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1581. Min Act: -0.1700

Data Index: 644236 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1388. Min Act: -0.1700

Data Index: 7438174 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1391. Min Act: -0.1700

Data Index: 1828961 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1124. Min Act: -0.1700

Data Index: 4629956 (Open Web Text)

Max Activating Token Index: 614

Text #11

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1243. Min Act: -0.1700

Data Index: 4934043 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1100. Min Act: -0.1700

Data Index: 2669156 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1173. Min Act: -0.1700

Data Index: 7307340 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1075. Min Act: -0.1700

Data Index: 3400182 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.0963. Min Act: -0.1700

Data Index: 7524464 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1146. Min Act: -0.1700

Data Index: 2556357 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1135. Min Act: -0.1700

Data Index: 4022609 (Open Web Text)

Max Activating Token Index: 374

Text #18

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.1298. Min Act: -0.1700

Data Index: 7297067 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 3.2967. Min Range: -3.2967

Max Act: 3.0990. Min Act: -0.1700

Data Index: 1933420 (Open Web Text)

Max Activating Token Index: 730