Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6165 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3937836 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.9246. Min Act: -0.1700
Data Index: 6340189 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7996. Min Act: -0.1700
Data Index: 1098681 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7683. Min Act: -0.1700
Data Index: 7717055 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7683. Min Act: -0.1700
Data Index: 25514 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7371. Min Act: -0.1700
Data Index: 8535028 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 8683088 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2801356 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 7681204 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 6504602 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2514206 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6746. Min Act: -0.1700
Data Index: 3553514 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.7058. Min Act: -0.1700
Data Index: 1143626 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6746. Min Act: -0.1700
Data Index: 7438979 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6746. Min Act: -0.1700
Data Index: 87199 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6746. Min Act: -0.1700
Data Index: 4115650 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6433. Min Act: -0.1700
Data Index: 6826296 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6433. Min Act: -0.1700
Data Index: 5384259 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6433. Min Act: -0.1700
Data Index: 6923355 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9871. Min Range: -4.9871
Max Act: 4.6433. Min Act: -0.1700
Data Index: 8117710 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19