Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.9197. Min Act: -0.1700
Data Index: 8096740 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1086228 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.9197. Min Act: -0.1700
Data Index: 7537997 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8572. Min Act: -0.1700
Data Index: 6071306 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8884. Min Act: -0.1700
Data Index: 3982451 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8884. Min Act: -0.1700
Data Index: 6825576 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8572. Min Act: -0.1700
Data Index: 8600117 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8572. Min Act: -0.1700
Data Index: 4646466 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8259. Min Act: -0.1700
Data Index: 7032990 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7947. Min Act: -0.1700
Data Index: 4140717 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8259. Min Act: -0.1700
Data Index: 841298 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8259. Min Act: -0.1700
Data Index: 7245202 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7947. Min Act: -0.1700
Data Index: 7956092 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.8259. Min Act: -0.1700
Data Index: 8202499 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7947. Min Act: -0.1700
Data Index: 1189582 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7634. Min Act: -0.1700
Data Index: 5735785 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7634. Min Act: -0.1700
Data Index: 7157272 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7322. Min Act: -0.1700
Data Index: 7012358 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7634. Min Act: -0.1700
Data Index: 7088925 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9509. Min Range: -4.9509
Max Act: 4.7634. Min Act: -0.1700
Data Index: 7538001 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19