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

Dataset: Open Web Text

Neuron 249 in Layer 5

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: 4.1396. Min Range: -4.1396

Max Act: 4.1396. Min Act: -0.1700

Data Index: 2083794 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 4.1396. Min Range: -4.1396

Max Act: 4.0930. Min Act: -0.1700

Data Index: 2985355 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 4.1396. Min Range: -4.1396

Max Act: 4.0362. Min Act: -0.1700

Data Index: 2747622 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9824. Min Act: -0.1700

Data Index: 6300196 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9387. Min Act: -0.1700

Data Index: 8180324 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9493. Min Act: -0.1700

Data Index: 8199995 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9178. Min Act: -0.1700

Data Index: 5599881 (Open Web Text)

Max Activating Token Index: 849

Text #7

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9085. Min Act: -0.1700

Data Index: 5684719 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9356. Min Act: -0.1700

Data Index: 3397156 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9878. Min Act: -0.1700

Data Index: 8626090 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9082. Min Act: -0.1700

Data Index: 6323974 (Open Web Text)

Max Activating Token Index: 85

Text #11

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9216. Min Act: -0.1700

Data Index: 6654671 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8995. Min Act: -0.1700

Data Index: 2170394 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8751. Min Act: -0.1700

Data Index: 8488133 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.9059. Min Act: -0.1700

Data Index: 6388838 (Open Web Text)

Max Activating Token Index: 428

Text #15

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8634. Min Act: -0.1700

Data Index: 6553818 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8806. Min Act: -0.1700

Data Index: 6622549 (Open Web Text)

Max Activating Token Index: 438

Text #17

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8472. Min Act: -0.1700

Data Index: 3594710 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8696. Min Act: -0.1700

Data Index: 4135852 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 4.1396. Min Range: -4.1396

Max Act: 3.8668. Min Act: -0.1700

Data Index: 4993801 (Open Web Text)

Max Activating Token Index: 960