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

Dataset: Open Web Text

Neuron 628 in Layer 1

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: 1.6446. Min Range: -1.6446

Max Act: 1.6446. Min Act: -0.1700

Data Index: 5703008 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.6138. Min Act: -0.1700

Data Index: 7890341 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5935. Min Act: -0.1692

Data Index: 2999772 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5979. Min Act: -0.1700

Data Index: 5132543 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5928. Min Act: -0.1700

Data Index: 4125107 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5928. Min Act: -0.1698

Data Index: 8041106 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5826. Min Act: -0.1700

Data Index: 4969927 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5681. Min Act: -0.1671

Data Index: 5162382 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5676. Min Act: -0.1700

Data Index: 6700269 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5541. Min Act: -0.1699

Data Index: 7377875 (Open Web Text)

Max Activating Token Index: 162

Text #10

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5584. Min Act: -0.1700

Data Index: 2204775 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5608. Min Act: -0.1694

Data Index: 4239847 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5495. Min Act: -0.1700

Data Index: 2200726 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5573. Min Act: -0.1700

Data Index: 7848676 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5548. Min Act: -0.1700

Data Index: 6404271 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5477. Min Act: -0.1697

Data Index: 5162383 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5409. Min Act: -0.1700

Data Index: 3317965 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5501. Min Act: -0.1694

Data Index: 1187069 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5439. Min Act: -0.1698

Data Index: 7891362 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.5474. Min Act: -0.1700

Data Index: 2530597 (Open Web Text)

Max Activating Token Index: 21