Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.8842. Min Act: -0.1700
Data Index: 1012332 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7592. Min Act: -0.1700
Data Index: 1782162 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7280. Min Act: -0.1700
Data Index: 1343447 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7280. Min Act: -0.1700
Data Index: 7383909 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7280. Min Act: -0.1700
Data Index: 7575407 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7280. Min Act: -0.1700
Data Index: 8832664 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6967. Min Act: -0.1700
Data Index: 2881762 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.7280. Min Act: -0.1700
Data Index: 5638716 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6967. Min Act: -0.1700
Data Index: 6895147 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6967. Min Act: -0.1700
Data Index: 7095883 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6967. Min Act: -0.1700
Data Index: 5710803 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6967. Min Act: -0.1700
Data Index: 856180 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6655. Min Act: -0.1700
Data Index: 6390700 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6342. Min Act: -0.1700
Data Index: 6278894 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6342. Min Act: -0.1700
Data Index: 2697267 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.5717. Min Act: -0.1700
Data Index: 4082000 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6030. Min Act: -0.1700
Data Index: 2774124 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.5717. Min Act: -0.1700
Data Index: 3996790 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.6342. Min Act: -0.1700
Data Index: 5776075 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8842. Min Range: -5.8842
Max Act: 5.5717. Min Act: -0.1700
Data Index: 5522095 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19