Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.8758. Min Act: -0.1700
Data Index: 5581198 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.7821. Min Act: -0.1700
Data Index: 41531 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.7821. Min Act: -0.1700
Data Index: 2699375 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.7508. Min Act: -0.1700
Data Index: 2804750 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5946. Min Act: -0.1700
Data Index: 7018725 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5633. Min Act: -0.1700
Data Index: 3274136 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5321. Min Act: -0.1700
Data Index: 1726029 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5321. Min Act: -0.1700
Data Index: 7466726 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5008. Min Act: -0.1700
Data Index: 8687649 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5966107 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5321. Min Act: -0.1700
Data Index: 4593526 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5416434 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5008. Min Act: -0.1700
Data Index: 2804754 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.4696. Min Act: -0.1700
Data Index: 5102101 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.5008. Min Act: -0.1700
Data Index: 4905106 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.4383. Min Act: -0.1700
Data Index: 5102100 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.4383. Min Act: -0.1700
Data Index: 2804743 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.4071. Min Act: -0.1700
Data Index: 2804752 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.4071. Min Act: -0.1700
Data Index: 1162864 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8758. Min Range: -5.8758
Max Act: 5.3446. Min Act: -0.1700
Data Index: 7834940 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19