Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3750. Min Range: -9.3750
Max Act: 9.3750. Min Act: -0.1700
Data Index: 4075620 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3750. Min Range: -9.3750
Max Act: 9.0000. Min Act: -0.1700
Data Index: 7552502 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.9375. Min Act: -0.1700
Data Index: 3519780 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.9375. Min Act: -0.1700
Data Index: 2756034 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.8125. Min Act: -0.1700
Data Index: 3537156 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.8125. Min Act: -0.1700
Data Index: 2211593 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.8125. Min Act: -0.1700
Data Index: 7551122 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.7500. Min Act: -0.1700
Data Index: 3631895 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.7500. Min Act: -0.1700
Data Index: 519766 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 437040 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 3086953 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 2811207 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 5559209 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 5128321 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 8593011 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6250. Min Act: -0.1700
Data Index: 6750970 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.6250. Min Act: -0.1700
Data Index: 8277392 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 4843246 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 3278333 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3750. Min Range: -9.3750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 223821 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19