Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1284 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.1842. Min Act: -0.1700
Data Index: 583118 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.1842. Min Act: -0.1700
Data Index: 1303342 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.1212. Min Act: -0.1700
Data Index: 4733108 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.1054. Min Act: -0.1700
Data Index: 2703717 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0897. Min Act: -0.1700
Data Index: 51110 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0897. Min Act: -0.1700
Data Index: 2189413 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0739. Min Act: -0.1700
Data Index: 2436873 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0581. Min Act: -0.1700
Data Index: 3129332 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0424. Min Act: -0.1700
Data Index: 5028797 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0266. Min Act: -0.1700
Data Index: 5289358 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0266. Min Act: -0.1700
Data Index: 417033 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9792. Min Act: -0.1700
Data Index: 8417145 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9950. Min Act: -0.1700
Data Index: 3873136 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1842. Min Range: -3.1842
Max Act: 3.0108. Min Act: -0.1700
Data Index: 5793986 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9792. Min Act: -0.1700
Data Index: 2114462 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9633. Min Act: -0.1700
Data Index: 2970726 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9633. Min Act: -0.1700
Data Index: 3423133 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9475. Min Act: -0.1700
Data Index: 3964075 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9475. Min Act: -0.1700
Data Index: 446536 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1842. Min Range: -3.1842
Max Act: 2.9475. Min Act: -0.1700
Data Index: 372627 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19