Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.7698. Min Act: -0.1700
Data Index: 5574476 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.7698. Min Act: -0.1700
Data Index: 459948 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.7072. Min Act: -0.1700
Data Index: 1597518 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6759. Min Act: -0.1700
Data Index: 4353424 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 6070014 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 1330351 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 5375854 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 2784554 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 182375 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 8290905 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 2386994 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6446. Min Act: -0.1700
Data Index: 4537528 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 228700 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 637930 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 288033 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 6070023 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 6070015 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 1542811 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 7344847 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7698. Min Range: -3.7698
Max Act: 3.6133. Min Act: -0.1700
Data Index: 7477067 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19