Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 350 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.9887. Min Act: -0.1700
Data Index: 6611329 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.8949. Min Act: -0.1700
Data Index: 2242786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.7387. Min Act: -0.1700
Data Index: 4073381 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.7387. Min Act: -0.1700
Data Index: 4287580 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4018940 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.7074. Min Act: -0.1700
Data Index: 6469534 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.6449. Min Act: -0.1700
Data Index: 5771882 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5824. Min Act: -0.1700
Data Index: 5874260 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5824. Min Act: -0.1700
Data Index: 6219704 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5824. Min Act: -0.1700
Data Index: 2669462 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5824. Min Act: -0.1700
Data Index: 1607 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5824. Min Act: -0.1700
Data Index: 7547557 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5512. Min Act: -0.1700
Data Index: 6847543 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5199. Min Act: -0.1700
Data Index: 27342 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5199. Min Act: -0.1700
Data Index: 6061137 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.4887. Min Act: -0.1700
Data Index: 4692692 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5199. Min Act: -0.1700
Data Index: 4254195 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5512. Min Act: -0.1700
Data Index: 264290 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.5199. Min Act: -0.1700
Data Index: 4264973 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9887. Min Range: -5.9887
Max Act: 5.4887. Min Act: -0.1700
Data Index: 6580457 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19