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

Dataset: Open Web Text

Neuron 1237 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: 4.8042. Min Range: -4.8042

Max Act: 4.8042. Min Act: -0.1700

Data Index: 5034699 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.7052. Min Act: -0.1700

Data Index: 157340 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.7356. Min Act: -0.1700

Data Index: 633548 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.7504. Min Act: -0.1700

Data Index: 5300614 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6769. Min Act: -0.1700

Data Index: 1291889 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.7258. Min Act: -0.1700

Data Index: 7900546 (Open Web Text)

Max Activating Token Index: 788

Text #6

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6378. Min Act: -0.1700

Data Index: 855031 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5998. Min Act: -0.1700

Data Index: 5254990 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6349. Min Act: -0.1700

Data Index: 1753856 (Open Web Text)

Max Activating Token Index: 991

Text #9

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5724. Min Act: -0.1700

Data Index: 8014596 (Open Web Text)

Max Activating Token Index: 295

Text #10

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5633. Min Act: -0.1700

Data Index: 4172353 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5381. Min Act: -0.1700

Data Index: 4316949 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5108. Min Act: -0.1700

Data Index: 6222714 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5386. Min Act: -0.1700

Data Index: 3684239 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5806. Min Act: -0.1700

Data Index: 3092397 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4764. Min Act: -0.1700

Data Index: 3352641 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4939. Min Act: -0.1700

Data Index: 4674907 (Open Web Text)

Max Activating Token Index: 765

Text #17

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4951. Min Act: -0.1700

Data Index: 6584487 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4528. Min Act: -0.1700

Data Index: 626885 (Open Web Text)

Max Activating Token Index: 614

Text #19

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4269. Min Act: -0.1700

Data Index: 2529058 (Open Web Text)

Max Activating Token Index: 485