Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0594. Min Range: -6.0594
Max Act: 6.0594. Min Act: -0.1700
Data Index: 3763468 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0594. Min Range: -6.0594
Max Act: 6.0281. Min Act: -0.1700
Data Index: 2360996 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.9344. Min Act: -0.1700
Data Index: 7167349 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.9344. Min Act: -0.1700
Data Index: 5420240 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.8719. Min Act: -0.1700
Data Index: 1370294 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7776001 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7910362 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.8719. Min Act: -0.1700
Data Index: 2469673 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.8406. Min Act: -0.1700
Data Index: 5212626 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7781. Min Act: -0.1700
Data Index: 5890267 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7781. Min Act: -0.1700
Data Index: 1601644 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7781. Min Act: -0.1700
Data Index: 3583629 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7781. Min Act: -0.1700
Data Index: 7195980 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4185946 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7469. Min Act: -0.1700
Data Index: 292668 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7469. Min Act: -0.1700
Data Index: 3235333 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5546253 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2647297 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2638711 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0594. Min Range: -6.0594
Max Act: 5.6844. Min Act: -0.1700
Data Index: 4498641 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19