Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0456. Min Range: -7.0456
Max Act: 7.0456. Min Act: -0.1700
Data Index: 4371889 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0456. Min Range: -7.0456
Max Act: 7.0143. Min Act: -0.1700
Data Index: 5543298 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.8893. Min Act: -0.1700
Data Index: 1639792 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.8893. Min Act: -0.1700
Data Index: 339 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.8893. Min Act: -0.1700
Data Index: 4933503 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7956. Min Act: -0.1700
Data Index: 8022213 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7643. Min Act: -0.1700
Data Index: 1228932 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7018. Min Act: -0.1700
Data Index: 5844672 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7018. Min Act: -0.1700
Data Index: 8722144 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7018. Min Act: -0.1700
Data Index: 7965019 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6706. Min Act: -0.1700
Data Index: 5570856 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7018. Min Act: -0.1700
Data Index: 5583159 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6706. Min Act: -0.1700
Data Index: 3194520 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6706. Min Act: -0.1700
Data Index: 6445415 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6706. Min Act: -0.1700
Data Index: 3456573 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6393. Min Act: -0.1700
Data Index: 3054517 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6393. Min Act: -0.1700
Data Index: 6398803 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6081. Min Act: -0.1700
Data Index: 6472518 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6081. Min Act: -0.1700
Data Index: 2241102 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5768. Min Act: -0.1700
Data Index: 5567611 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19