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

Dataset: Open Web Text

Neuron 54 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: 5.0342. Min Range: -5.0342

Max Act: 5.0342. Min Act: -0.1700

Data Index: 7316293 (Open Web Text)

Max Activating Token Index: 68

Text #1

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8834. Min Act: -0.1700

Data Index: 4538938 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8428. Min Act: -0.1700

Data Index: 6540442 (Open Web Text)

Max Activating Token Index: 533

Text #3

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8011. Min Act: -0.1700

Data Index: 4122054 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.7480. Min Act: -0.1700

Data Index: 5988518 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.7629. Min Act: -0.1700

Data Index: 892796 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.7374. Min Act: -0.1700

Data Index: 1742559 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6925. Min Act: -0.1700

Data Index: 7351247 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.7282. Min Act: -0.1700

Data Index: 2254597 (Open Web Text)

Max Activating Token Index: 157

Text #9

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6058. Min Act: -0.1700

Data Index: 1489688 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.5998. Min Act: -0.1700

Data Index: 1919186 (Open Web Text)

Max Activating Token Index: 283

Text #11

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6473. Min Act: -0.1700

Data Index: 6708794 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6190. Min Act: -0.1700

Data Index: 535268 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1515718 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6128. Min Act: -0.1700

Data Index: 304174 (Open Web Text)

Max Activating Token Index: 196

Text #15

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6119. Min Act: -0.1700

Data Index: 3575363 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.5773. Min Act: -0.1700

Data Index: 8185875 (Open Web Text)

Max Activating Token Index: 308

Text #17

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.5999. Min Act: -0.1700

Data Index: 1079987 (Open Web Text)

Max Activating Token Index: 229

Text #18

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.6001. Min Act: -0.1700

Data Index: 4161600 (Open Web Text)

Max Activating Token Index: 788

Text #19

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.5415. Min Act: -0.1700

Data Index: 6318413 (Open Web Text)

Max Activating Token Index: 732