Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 597 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.3349. Min Act: -0.1700
Data Index: 5206670 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.3037. Min Act: -0.1700
Data Index: 2253764 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.3349. Min Act: -0.1700
Data Index: 8352736 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.2412. Min Act: -0.1700
Data Index: 1493526 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.2724. Min Act: -0.1700
Data Index: 7013713 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 4714481 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6570231 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 3003378 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 5867760 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.2099. Min Act: -0.1700
Data Index: 2988454 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1474. Min Act: -0.1700
Data Index: 5330425 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 820601 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 8277540 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.2099. Min Act: -0.1700
Data Index: 2690955 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 7092547 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 562538 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1787. Min Act: -0.1700
Data Index: 4961968 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6103764 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1474. Min Act: -0.1700
Data Index: 430254 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3349. Min Range: -5.3349
Max Act: 5.1474. Min Act: -0.1700
Data Index: 4972433 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19