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

Dataset: Open Web Text

Neuron 2725 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: 4.0484. Min Range: -4.0484

Max Act: 4.0484. Min Act: -0.1700

Data Index: 774722 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.9095. Min Act: -0.1700

Data Index: 8750244 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.8534. Min Act: -0.1700

Data Index: 8264568 (Open Web Text)

Max Activating Token Index: 723

Text #3

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7543. Min Act: -0.1700

Data Index: 3016879 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.8267. Min Act: -0.1700

Data Index: 3534175 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.9017. Min Act: -0.1700

Data Index: 5318823 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7906. Min Act: -0.1700

Data Index: 7407494 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7976. Min Act: -0.1700

Data Index: 4829736 (Open Web Text)

Max Activating Token Index: 678

Text #8

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7547. Min Act: -0.1700

Data Index: 5820474 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7999. Min Act: -0.1700

Data Index: 5331530 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.8432. Min Act: -0.1700

Data Index: 5237093 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7453. Min Act: -0.1700

Data Index: 5009915 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7531. Min Act: -0.1700

Data Index: 3534777 (Open Web Text)

Max Activating Token Index: 909

Text #13

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7779. Min Act: -0.1700

Data Index: 4136820 (Open Web Text)

Max Activating Token Index: 223

Text #14

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.8123. Min Act: -0.1700

Data Index: 5604775 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7293. Min Act: -0.1700

Data Index: 5880105 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7208. Min Act: -0.1699

Data Index: 4490287 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7515. Min Act: -0.1700

Data Index: 6524027 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7093. Min Act: -0.1700

Data Index: 6883274 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 4.0484. Min Range: -4.0484

Max Act: 3.7570. Min Act: -0.1700

Data Index: 1404323 (Open Web Text)

Max Activating Token Index: 64