Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5678 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1288. Min Range: -10.1288
Max Act: 10.1288. Min Act: -0.1700
Data Index: 6482048 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1288. Min Range: -10.1288
Max Act: 10.0663. Min Act: -0.1700
Data Index: 4958521 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1288. Min Range: -10.1288
Max Act: 10.0038. Min Act: -0.1700
Data Index: 6587214 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1288. Min Range: -10.1288
Max Act: 10.0038. Min Act: -0.1700
Data Index: 7012826 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 1533306 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 4696143 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8163. Min Act: -0.1700
Data Index: 5441274 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 1773509 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 5971941 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 2087705 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 2023842 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8788. Min Act: -0.1700
Data Index: 2859386 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8163. Min Act: -0.1700
Data Index: 337108 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.8163. Min Act: -0.1700
Data Index: 15862 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.7538. Min Act: -0.1700
Data Index: 3621809 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.6913. Min Act: -0.1700
Data Index: 1679766 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.7538. Min Act: -0.1700
Data Index: 6150385 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.7538. Min Act: -0.1700
Data Index: 4083675 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.7538. Min Act: -0.1700
Data Index: 2191748 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1288. Min Range: -10.1288
Max Act: 9.6913. Min Act: -0.1700
Data Index: 1145286 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19