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

Dataset: Open Web Text

Neuron 2302 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: 4.0525. Min Range: -4.0525

Max Act: 4.0525. Min Act: -0.1700

Data Index: 760689 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0008. Min Act: -0.1700

Data Index: 8508877 (Open Web Text)

Max Activating Token Index: 255

Text #2

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8731. Min Act: -0.1700

Data Index: 337435 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8694. Min Act: -0.1700

Data Index: 4814519 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8632. Min Act: -0.1700

Data Index: 2725924 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8838. Min Act: -0.1700

Data Index: 962382 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1387321 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8701. Min Act: -0.1700

Data Index: 3272002 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8429. Min Act: -0.1700

Data Index: 1209771 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8178. Min Act: -0.1700

Data Index: 4075313 (Open Web Text)

Max Activating Token Index: 222

Text #10

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8420. Min Act: -0.1700

Data Index: 3718649 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8431. Min Act: -0.1700

Data Index: 3330142 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8280. Min Act: -0.1700

Data Index: 5442374 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8646. Min Act: -0.1700

Data Index: 7118514 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8484. Min Act: -0.1700

Data Index: 147024 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8115. Min Act: -0.1700

Data Index: 7315745 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8049. Min Act: -0.1700

Data Index: 5823048 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8142. Min Act: -0.1700

Data Index: 1071754 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8096. Min Act: -0.1700

Data Index: 4942114 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8076. Min Act: -0.1700

Data Index: 1318736 (Open Web Text)

Max Activating Token Index: 539