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

Dataset: Open Web Text

Neuron 1875 in Layer 6

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: 3.0453. Min Range: -3.0453

Max Act: 3.0453. Min Act: -0.1700

Data Index: 7008497 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.9010. Min Act: -0.1700

Data Index: 8697071 (Open Web Text)

Max Activating Token Index: 652

Text #2

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8498. Min Act: -0.1700

Data Index: 3559820 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8347. Min Act: -0.1700

Data Index: 6895004 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8317. Min Act: -0.1700

Data Index: 2679590 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8285. Min Act: -0.1700

Data Index: 5588098 (Open Web Text)

Max Activating Token Index: 680

Text #6

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7998. Min Act: -0.1700

Data Index: 7326311 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8180. Min Act: -0.1700

Data Index: 3303998 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7892. Min Act: -0.1700

Data Index: 2326632 (Open Web Text)

Max Activating Token Index: 984

Text #9

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7896. Min Act: -0.1700

Data Index: 4355567 (Open Web Text)

Max Activating Token Index: 115

Text #10

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7751. Min Act: -0.1700

Data Index: 107759 (Open Web Text)

Max Activating Token Index: 921

Text #11

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7810. Min Act: -0.1700

Data Index: 2281716 (Open Web Text)

Max Activating Token Index: 196

Text #12

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7740. Min Act: -0.1700

Data Index: 5045961 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7690. Min Act: -0.1700

Data Index: 4992499 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7665. Min Act: -0.1700

Data Index: 6777881 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7810. Min Act: -0.1700

Data Index: 1622259 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7574. Min Act: -0.1700

Data Index: 3108444 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7549. Min Act: -0.1700

Data Index: 1085592 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7819. Min Act: -0.1700

Data Index: 1558782 (Open Web Text)

Max Activating Token Index: 913

Text #19

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.7401. Min Act: -0.1700

Data Index: 3517067 (Open Web Text)

Max Activating Token Index: 639