Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5399 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.2626. Min Act: -0.1700
Data Index: 7054754 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.2001. Min Act: -0.1700
Data Index: 5698957 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.2001. Min Act: -0.1700
Data Index: 5678910 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0751. Min Act: -0.1700
Data Index: 8780044 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0751. Min Act: -0.1700
Data Index: 6265037 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0126. Min Act: -0.1700
Data Index: 7877937 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0126. Min Act: -0.1700
Data Index: 2601863 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0126. Min Act: -0.1700
Data Index: 5089708 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2626. Min Range: -8.2626
Max Act: 8.0126. Min Act: -0.1700
Data Index: 4829777 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.9501. Min Act: -0.1700
Data Index: 8411231 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.9501. Min Act: -0.1700
Data Index: 8430611 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.9501. Min Act: -0.1700
Data Index: 1030134 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.9501. Min Act: -0.1700
Data Index: 7000247 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8251. Min Act: -0.1700
Data Index: 6348631 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8251. Min Act: -0.1700
Data Index: 556371 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8251. Min Act: -0.1700
Data Index: 4028275 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8251. Min Act: -0.1700
Data Index: 6364339 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8876. Min Act: -0.1700
Data Index: 3402215 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.8251. Min Act: -0.1700
Data Index: 890982 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2626. Min Range: -8.2626
Max Act: 7.7939. Min Act: -0.1700
Data Index: 7991971 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19