Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1508. Min Range: -6.1508
Max Act: 6.1508. Min Act: -0.1700
Data Index: 3790190 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1508. Min Range: -6.1508
Max Act: 6.0883. Min Act: -0.1700
Data Index: 8614282 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1508. Min Range: -6.1508
Max Act: 6.0570. Min Act: -0.1700
Data Index: 5642214 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1508. Min Range: -6.1508
Max Act: 6.0258. Min Act: -0.1700
Data Index: 69996 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.9633. Min Act: -0.1700
Data Index: 5522108 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.9008. Min Act: -0.1700
Data Index: 1239570 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 3211075 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 5021617 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 6178644 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.9008. Min Act: -0.1700
Data Index: 6443787 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8383. Min Act: -0.1700
Data Index: 6860499 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 1373778 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8383. Min Act: -0.1700
Data Index: 4768037 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8070. Min Act: -0.1700
Data Index: 7067379 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 6052815 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8695. Min Act: -0.1700
Data Index: 7321074 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8070. Min Act: -0.1700
Data Index: 4158521 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.7758. Min Act: -0.1700
Data Index: 966546 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8070. Min Act: -0.1700
Data Index: 6546066 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1508. Min Range: -6.1508
Max Act: 5.8070. Min Act: -0.1700
Data Index: 7373360 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19