Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5723. Min Act: -0.1700
Data Index: 7638661 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5567. Min Act: -0.1700
Data Index: 6035539 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5253. Min Act: -0.1700
Data Index: 8524862 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5097. Min Act: -0.1700
Data Index: 5261163 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5097. Min Act: -0.1700
Data Index: 574812 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5097. Min Act: -0.1700
Data Index: 204680 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.5097. Min Act: -0.1700
Data Index: 6035547 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4940. Min Act: -0.1700
Data Index: 204678 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4940. Min Act: -0.1700
Data Index: 3260787 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4627. Min Act: -0.1700
Data Index: 6035526 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4470. Min Act: -0.1700
Data Index: 4626325 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4157. Min Act: -0.1700
Data Index: 3233907 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4313. Min Act: -0.1700
Data Index: 2385110 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4157. Min Act: -0.1700
Data Index: 144234 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4157. Min Act: -0.1700
Data Index: 684775 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.4000. Min Act: -0.1700
Data Index: 7269085 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.3843. Min Act: -0.1700
Data Index: 2359083 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.3843. Min Act: -0.1700
Data Index: 4971756 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.3843. Min Act: -0.1700
Data Index: 2531486 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5723. Min Range: -3.5723
Max Act: 3.3686. Min Act: -0.1700
Data Index: 1576749 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19