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

Dataset: Open Web Text

Neuron 625 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: 5.3346. Min Range: -5.3346

Max Act: 5.3346. Min Act: -0.1700

Data Index: 3046769 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.2237. Min Act: -0.1700

Data Index: 1762298 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1913. Min Act: -0.1700

Data Index: 7684897 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.2262. Min Act: -0.1700

Data Index: 3808338 (Open Web Text)

Max Activating Token Index: 738

Text #4

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1729. Min Act: -0.1700

Data Index: 3808342 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1778. Min Act: -0.1700

Data Index: 5027850 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1344. Min Act: -0.1700

Data Index: 3259784 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1256. Min Act: -0.1700

Data Index: 6963340 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.1356. Min Act: -0.1700

Data Index: 4913805 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0936. Min Act: -0.1700

Data Index: 5871639 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0979. Min Act: -0.1700

Data Index: 2526365 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0962. Min Act: -0.1700

Data Index: 7038422 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0930. Min Act: -0.1700

Data Index: 3951579 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0744. Min Act: -0.1700

Data Index: 3394696 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0640. Min Act: -0.1700

Data Index: 3190912 (Open Web Text)

Max Activating Token Index: 693

Text #15

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0746. Min Act: -0.1700

Data Index: 6277868 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0773. Min Act: -0.1700

Data Index: 1183929 (Open Web Text)

Max Activating Token Index: 474

Text #17

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0643. Min Act: -0.1700

Data Index: 6404522 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0476. Min Act: -0.1700

Data Index: 4396675 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 5.3346. Min Range: -5.3346

Max Act: 5.0785. Min Act: -0.1700

Data Index: 3332971 (Open Web Text)

Max Activating Token Index: 144