Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.7239. Min Act: -0.1700
Data Index: 1946284 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 7482840 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 826717 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 3140603 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 6295355 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 6026776 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1810959 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6614. Min Act: -0.1700
Data Index: 4489262 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 3975296 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 6626040 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 2947433 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 2768039 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 4621595 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 7087309 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 4587181 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 5936249 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 4563770 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.6302. Min Act: -0.1700
Data Index: 6120476 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.5989. Min Act: -0.1700
Data Index: 3543114 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7239. Min Range: -5.7239
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2105767 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19