Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8807. Min Range: -8.8807
Max Act: 8.8807. Min Act: -0.1700
Data Index: 8471592 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8807. Min Range: -8.8807
Max Act: 8.4432. Min Act: -0.1700
Data Index: 1318179 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8807. Min Range: -8.8807
Max Act: 8.2557. Min Act: -0.1700
Data Index: 2536758 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8807. Min Range: -8.8807
Max Act: 8.3182. Min Act: -0.1700
Data Index: 8551246 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8807. Min Range: -8.8807
Max Act: 8.2557. Min Act: -0.1700
Data Index: 783253 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.9432. Min Act: -0.1700
Data Index: 6145938 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7870. Min Act: -0.1700
Data Index: 4294038 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7870. Min Act: -0.1700
Data Index: 5805286 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7557. Min Act: -0.1700
Data Index: 486851 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7557. Min Act: -0.1700
Data Index: 4373087 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7245. Min Act: -0.1700
Data Index: 2166938 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7245. Min Act: -0.1700
Data Index: 1183496 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.7245. Min Act: -0.1700
Data Index: 4188149 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6932. Min Act: -0.1700
Data Index: 1292659 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6620. Min Act: -0.1700
Data Index: 6147540 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6620. Min Act: -0.1700
Data Index: 8004520 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6620. Min Act: -0.1700
Data Index: 1405577 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6307. Min Act: -0.1700
Data Index: 8335927 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6307. Min Act: -0.1700
Data Index: 8595414 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8807. Min Range: -8.8807
Max Act: 7.6307. Min Act: -0.1700
Data Index: 8533533 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19