Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.3768. Min Act: -0.1700
Data Index: 6373511 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.3143. Min Act: -0.1700
Data Index: 2578046 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.2831. Min Act: -0.1700
Data Index: 8612471 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.1893. Min Act: -0.1700
Data Index: 475354 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.1581. Min Act: -0.1700
Data Index: 8068305 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0956. Min Act: -0.1700
Data Index: 8105444 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0956. Min Act: -0.1700
Data Index: 4719122 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0331. Min Act: -0.1700
Data Index: 3363918 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0018. Min Act: -0.1700
Data Index: 4480965 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0331. Min Act: -0.1700
Data Index: 4194320 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3768. Min Range: -6.3768
Max Act: 6.0018. Min Act: -0.1700
Data Index: 6832217 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9706. Min Act: -0.1700
Data Index: 772689 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5273447 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9706. Min Act: -0.1700
Data Index: 6786553 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3693920 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9706. Min Act: -0.1700
Data Index: 3370672 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9081. Min Act: -0.1700
Data Index: 7149808 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.9081. Min Act: -0.1700
Data Index: 1730879 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.8768. Min Act: -0.1700
Data Index: 2307623 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3768. Min Range: -6.3768
Max Act: 5.8456. Min Act: -0.1700
Data Index: 6168863 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19