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

Dataset: Open Web Text

Neuron 2065 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: 3.1879. Min Range: -3.1879

Max Act: 3.1879. Min Act: -0.1700

Data Index: 2415432 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1382. Min Act: -0.1700

Data Index: 4444317 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1399. Min Act: -0.1700

Data Index: 8191013 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1543. Min Act: -0.1700

Data Index: 8635884 (Open Web Text)

Max Activating Token Index: 319

Text #4

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1355. Min Act: -0.1700

Data Index: 4375517 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1183. Min Act: -0.1700

Data Index: 5777230 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1247. Min Act: -0.1700

Data Index: 8528255 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1082. Min Act: -0.1700

Data Index: 2996725 (Open Web Text)

Max Activating Token Index: 244

Text #8

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1079. Min Act: -0.1700

Data Index: 1916184 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1010. Min Act: -0.1700

Data Index: 2291170 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1233. Min Act: -0.1700

Data Index: 5568487 (Open Web Text)

Max Activating Token Index: 869

Text #11

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0930. Min Act: -0.1700

Data Index: 2427697 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0910. Min Act: -0.1700

Data Index: 4208633 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.1025. Min Act: -0.1700

Data Index: 7843318 (Open Web Text)

Max Activating Token Index: 948

Text #14

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0865. Min Act: -0.1700

Data Index: 6460273 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0796. Min Act: -0.1700

Data Index: 6147750 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0794. Min Act: -0.1700

Data Index: 5646645 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0904. Min Act: -0.1700

Data Index: 2890887 (Open Web Text)

Max Activating Token Index: 911

Text #18

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0707. Min Act: -0.1700

Data Index: 890556 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 3.1879. Min Range: -3.1879

Max Act: 3.0763. Min Act: -0.1700

Data Index: 3294442 (Open Web Text)

Max Activating Token Index: 849