Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 948 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.2508. Min Act: -0.1700
Data Index: 6804321 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7833799 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.1571. Min Act: -0.1700
Data Index: 8330474 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.1571. Min Act: -0.1700
Data Index: 3097770 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.1258. Min Act: -0.1700
Data Index: 7887467 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.1258. Min Act: -0.1700
Data Index: 1109114 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.0633. Min Act: -0.1700
Data Index: 6806207 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.0946. Min Act: -0.1700
Data Index: 636806 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.0633. Min Act: -0.1700
Data Index: 2817982 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.0008. Min Act: -0.1700
Data Index: 6033948 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9383. Min Act: -0.1700
Data Index: 8781327 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9071. Min Act: -0.1700
Data Index: 6551417 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9696. Min Act: -0.1700
Data Index: 4551393 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9383. Min Act: -0.1700
Data Index: 4192571 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9071. Min Act: -0.1700
Data Index: 3625723 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9071. Min Act: -0.1700
Data Index: 6524186 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9071. Min Act: -0.1700
Data Index: 572088 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8758. Min Act: -0.1700
Data Index: 1754882 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8758. Min Act: -0.1700
Data Index: 543365 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8446. Min Act: -0.1700
Data Index: 4122682 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19