Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.9341. Min Act: -0.1700
Data Index: 5384191 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.9341. Min Act: -0.1700
Data Index: 328095 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.8716. Min Act: -0.1700
Data Index: 4813212 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.8091. Min Act: -0.1700
Data Index: 328094 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.6841. Min Act: -0.1700
Data Index: 6731034 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.6216. Min Act: -0.1700
Data Index: 8430915 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.6216. Min Act: -0.1700
Data Index: 5562045 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.5591. Min Act: -0.1700
Data Index: 7006513 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.5591. Min Act: -0.1700
Data Index: 1404505 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.4341. Min Act: -0.1700
Data Index: 8127153 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.4341. Min Act: -0.1700
Data Index: 1597795 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.4341. Min Act: -0.1700
Data Index: 8225801 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 543110 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 8573850 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 3325997 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 1285606 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 5983104 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3716. Min Act: -0.1700
Data Index: 1003795 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.3091. Min Act: -0.1700
Data Index: 6201159 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9341. Min Range: -10.9341
Max Act: 10.2466. Min Act: -0.1700
Data Index: 8366276 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19