Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5677 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.6501. Min Act: -0.1700
Data Index: 6445042 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.6188. Min Act: -0.1700
Data Index: 650031 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.5876. Min Act: -0.1700
Data Index: 6306674 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.5251. Min Act: -0.1700
Data Index: 4081867 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.5563. Min Act: -0.1700
Data Index: 1625474 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4938. Min Act: -0.1700
Data Index: 3440992 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4626. Min Act: -0.1700
Data Index: 7140957 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4626. Min Act: -0.1700
Data Index: 6658525 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6040903 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4313. Min Act: -0.1700
Data Index: 945974 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.4001. Min Act: -0.1700
Data Index: 6351417 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.3063. Min Act: -0.1700
Data Index: 3442447 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.3063. Min Act: -0.1700
Data Index: 6664153 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.3063. Min Act: -0.1700
Data Index: 5039143 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.2751. Min Act: -0.1700
Data Index: 1956983 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.3063. Min Act: -0.1700
Data Index: 1319299 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.2751. Min Act: -0.1700
Data Index: 6035090 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.2438. Min Act: -0.1700
Data Index: 3783727 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.3063. Min Act: -0.1700
Data Index: 4194188 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6501. Min Range: -6.6501
Max Act: 6.2438. Min Act: -0.1700
Data Index: 3044614 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19