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

Dataset: Open Web Text

Neuron 1323 in Layer 4

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: 4.0940. Min Range: -4.0940

Max Act: 4.0940. Min Act: -0.1700

Data Index: 1694600 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0018. Min Act: -0.1700

Data Index: 6398387 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9440. Min Act: -0.1700

Data Index: 39415 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.7691. Min Act: -0.1700

Data Index: 2049992 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.7340. Min Act: -0.1700

Data Index: 5040548 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6962. Min Act: -0.1700

Data Index: 6354709 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.7362. Min Act: -0.1700

Data Index: 3680251 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6651. Min Act: -0.1700

Data Index: 6220335 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6757. Min Act: -0.1700

Data Index: 1945637 (Open Web Text)

Max Activating Token Index: 694

Text #9

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6661. Min Act: -0.1700

Data Index: 506203 (Open Web Text)

Max Activating Token Index: 884

Text #10

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6393. Min Act: -0.1700

Data Index: 6782223 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6456. Min Act: -0.1700

Data Index: 6709833 (Open Web Text)

Max Activating Token Index: 184

Text #12

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6245. Min Act: -0.1700

Data Index: 8627129 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.6243. Min Act: -0.1700

Data Index: 4014024 (Open Web Text)

Max Activating Token Index: 870

Text #14

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5870. Min Act: -0.1700

Data Index: 6457614 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5776. Min Act: -0.1700

Data Index: 1771158 (Open Web Text)

Max Activating Token Index: 823

Text #16

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5700. Min Act: -0.1700

Data Index: 6905947 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5784. Min Act: -0.1700

Data Index: 779889 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5494. Min Act: -0.1700

Data Index: 4786688 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5415. Min Act: -0.1700

Data Index: 3696157 (Open Web Text)

Max Activating Token Index: 702