Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.6375. Min Act: -0.1700
Data Index: 747836 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.5125. Min Act: -0.1700
Data Index: 6070890 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.4500. Min Act: -0.1700
Data Index: 6999749 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.4500. Min Act: -0.1700
Data Index: 1565278 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.3875. Min Act: -0.1700
Data Index: 4951315 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.3250. Min Act: -0.1700
Data Index: 6270744 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.2625. Min Act: -0.1700
Data Index: 1828554 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.3250. Min Act: -0.1700
Data Index: 3473862 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.3250. Min Act: -0.1700
Data Index: 3468062 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.3250. Min Act: -0.1700
Data Index: 3288143 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.2625. Min Act: -0.1700
Data Index: 2633191 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.2000. Min Act: -0.1700
Data Index: 5305408 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0750. Min Act: -0.1700
Data Index: 2801428 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.1375. Min Act: -0.1700
Data Index: 5734813 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0750. Min Act: -0.1700
Data Index: 8252776 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0750. Min Act: -0.1700
Data Index: 2870395 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0125. Min Act: -0.1700
Data Index: 5756043 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0125. Min Act: -0.1700
Data Index: 2437203 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6375. Min Range: -9.6375
Max Act: 9.0125. Min Act: -0.1700
Data Index: 5506546 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6375. Min Range: -9.6375
Max Act: 8.9500. Min Act: -0.1700
Data Index: 6861711 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19