Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.8931. Min Act: -0.1700
Data Index: 8416770 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7368. Min Act: -0.1700
Data Index: 7868960 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7368. Min Act: -0.1700
Data Index: 1041873 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7056. Min Act: -0.1700
Data Index: 1401974 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7056. Min Act: -0.1700
Data Index: 8416765 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7056. Min Act: -0.1700
Data Index: 3938757 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6743. Min Act: -0.1700
Data Index: 8416766 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6743. Min Act: -0.1700
Data Index: 5608203 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6743. Min Act: -0.1700
Data Index: 6129663 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6431. Min Act: -0.1700
Data Index: 1401973 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6431. Min Act: -0.1700
Data Index: 4609262 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6431. Min Act: -0.1700
Data Index: 7868962 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6118. Min Act: -0.1700
Data Index: 6658172 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6118. Min Act: -0.1700
Data Index: 6409283 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.6118. Min Act: -0.1700
Data Index: 564281 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5493. Min Act: -0.1700
Data Index: 1401971 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5806. Min Act: -0.1700
Data Index: 943958 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5493. Min Act: -0.1700
Data Index: 7868956 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5493. Min Act: -0.1700
Data Index: 3195477 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5493. Min Act: -0.1700
Data Index: 1401972 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19