Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.3685. Min Act: -0.1700
Data Index: 1819630 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.2743. Min Act: -0.1700
Data Index: 7256593 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.2743. Min Act: -0.1700
Data Index: 8382443 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.2429. Min Act: -0.1700
Data Index: 113936 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.2429. Min Act: -0.1700
Data Index: 6719669 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1800. Min Act: -0.1700
Data Index: 8233195 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1800. Min Act: -0.1700
Data Index: 280800 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1800. Min Act: -0.1700
Data Index: 8359356 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1800. Min Act: -0.1700
Data Index: 6455120 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1485. Min Act: -0.1700
Data Index: 446252 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1643. Min Act: -0.1700
Data Index: 7031424 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1643. Min Act: -0.1700
Data Index: 6220768 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1485. Min Act: -0.1700
Data Index: 7543948 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1643. Min Act: -0.1700
Data Index: 5366810 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1328. Min Act: -0.1700
Data Index: 8186589 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1485. Min Act: -0.1700
Data Index: 8257830 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1328. Min Act: -0.1700
Data Index: 8670185 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1328. Min Act: -0.1700
Data Index: 1836355 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1170. Min Act: -0.1700
Data Index: 6901358 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3685. Min Range: -3.3685
Max Act: 3.1170. Min Act: -0.1700
Data Index: 2318483 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19