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

Dataset: Open Web Text

Neuron 2380 in Layer 4

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: 5.6501. Min Range: -5.6501

Max Act: 5.6501. Min Act: -0.1700

Data Index: 1382970 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.5280. Min Act: -0.1700

Data Index: 3805287 (Open Web Text)

Max Activating Token Index: 855

Text #2

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.5227. Min Act: -0.1700

Data Index: 6973825 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.5743. Min Act: -0.1700

Data Index: 1637622 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4451. Min Act: -0.1700

Data Index: 776902 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4196. Min Act: -0.1700

Data Index: 1810778 (Open Web Text)

Max Activating Token Index: 780

Text #6

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4109. Min Act: -0.1700

Data Index: 3741506 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3820. Min Act: -0.1700

Data Index: 1436873 (Open Web Text)

Max Activating Token Index: 927

Text #8

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4198. Min Act: -0.1700

Data Index: 8203686 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4153. Min Act: -0.1700

Data Index: 7544510 (Open Web Text)

Max Activating Token Index: 403

Text #10

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3708. Min Act: -0.1700

Data Index: 93903 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3317. Min Act: -0.1700

Data Index: 1382969 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.4031. Min Act: -0.1700

Data Index: 4931976 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3119. Min Act: -0.1700

Data Index: 2432813 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.2979. Min Act: -0.1700

Data Index: 5924715 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3470. Min Act: -0.1700

Data Index: 4564399 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3618. Min Act: -0.1700

Data Index: 4059296 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3402. Min Act: -0.1700

Data Index: 6898450 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.3051. Min Act: -0.1700

Data Index: 2126663 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 5.6501. Min Range: -5.6501

Max Act: 5.2701. Min Act: -0.1700

Data Index: 6238185 (Open Web Text)

Max Activating Token Index: 425