Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 994 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0034. Min Range: -8.0034
Max Act: 8.0034. Min Act: -0.1700
Data Index: 2118724 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.4096. Min Act: -0.1700
Data Index: 610794 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.3159. Min Act: -0.1700
Data Index: 1591394 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1909. Min Act: -0.1700
Data Index: 503691 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1596. Min Act: -0.1700
Data Index: 4820306 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1909. Min Act: -0.1700
Data Index: 6322422 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1596. Min Act: -0.1700
Data Index: 5944254 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1596. Min Act: -0.1700
Data Index: 4188243 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.1284. Min Act: -0.1700
Data Index: 5088668 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.0971. Min Act: -0.1700
Data Index: 3351302 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.0659. Min Act: -0.1700
Data Index: 4117019 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.0659. Min Act: -0.1700
Data Index: 1377455 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.0346. Min Act: -0.1700
Data Index: 2291124 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0034. Min Range: -8.0034
Max Act: 7.0346. Min Act: -0.1700
Data Index: 4476202 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9721. Min Act: -0.1700
Data Index: 600118 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9409. Min Act: -0.1700
Data Index: 8368075 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9409. Min Act: -0.1700
Data Index: 5446447 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9096. Min Act: -0.1700
Data Index: 2833891 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9409. Min Act: -0.1700
Data Index: 1495853 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0034. Min Range: -8.0034
Max Act: 6.9096. Min Act: -0.1700
Data Index: 6171850 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19