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

Dataset: Open Web Text

Neuron 1575 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: 3.1768. Min Range: -3.1768

Max Act: 3.1768. Min Act: -0.1700

Data Index: 1062246 (Open Web Text)

Max Activating Token Index: 579

Text #1

Max Range: 3.1768. Min Range: -3.1768

Max Act: 3.1532. Min Act: -0.1700

Data Index: 535754 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9694. Min Act: -0.1700

Data Index: 2949238 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9317. Min Act: -0.1700

Data Index: 3376764 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9399. Min Act: -0.1700

Data Index: 7339299 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9372. Min Act: -0.1700

Data Index: 1929206 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9151. Min Act: -0.1700

Data Index: 6118220 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9561. Min Act: -0.1700

Data Index: 1429141 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9444. Min Act: -0.1700

Data Index: 4663004 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9448. Min Act: -0.1700

Data Index: 4663005 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9501. Min Act: -0.1700

Data Index: 6331301 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9251. Min Act: -0.1700

Data Index: 6651067 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9405. Min Act: -0.1700

Data Index: 7422957 (Open Web Text)

Max Activating Token Index: 795

Text #13

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8971. Min Act: -0.1700

Data Index: 6404097 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9170. Min Act: -0.1700

Data Index: 6420625 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8850. Min Act: -0.1700

Data Index: 4740181 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8850. Min Act: -0.1700

Data Index: 7094520 (Open Web Text)

Max Activating Token Index: 293

Text #17

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8882. Min Act: -0.1700

Data Index: 1166472 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9018. Min Act: -0.1700

Data Index: 7693455 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8855. Min Act: -0.1700

Data Index: 2983254 (Open Web Text)

Max Activating Token Index: 477