Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.7396. Min Act: -0.1700
Data Index: 8622298 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.7709. Min Act: -0.1700
Data Index: 6411872 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.6771. Min Act: -0.1700
Data Index: 1334967 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.6771. Min Act: -0.1700
Data Index: 6735128 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 8043257 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 8522962 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 3035688 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5834. Min Act: -0.1700
Data Index: 1436825 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5834. Min Act: -0.1700
Data Index: 7789115 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5209. Min Act: -0.1700
Data Index: 4544982 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5521. Min Act: -0.1700
Data Index: 167258 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5209. Min Act: -0.1700
Data Index: 3939073 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5209. Min Act: -0.1700
Data Index: 2214022 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.5209. Min Act: -0.1700
Data Index: 5639752 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4896. Min Act: -0.1700
Data Index: 92348 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4584. Min Act: -0.1700
Data Index: 1519084 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4584. Min Act: -0.1700
Data Index: 3462886 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4584. Min Act: -0.1700
Data Index: 4968668 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4271. Min Act: -0.1700
Data Index: 350369 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7709. Min Range: -4.7709
Max Act: 4.4584. Min Act: -0.1700
Data Index: 4893842 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19