Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.6693. Min Act: -0.1700
Data Index: 3054314 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.6693. Min Act: -0.1700
Data Index: 6710397 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.2318. Min Act: -0.1700
Data Index: 3245122 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.2005. Min Act: -0.1700
Data Index: 8521830 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5383168 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.1068. Min Act: -0.1700
Data Index: 947792 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.0130. Min Act: -0.1700
Data Index: 1190876 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.0130. Min Act: -0.1700
Data Index: 37149 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.0130. Min Act: -0.1700
Data Index: 5984710 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9818. Min Act: -0.1700
Data Index: 3144458 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9818. Min Act: -0.1700
Data Index: 8633409 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6693. Min Range: -5.6693
Max Act: 5.0130. Min Act: -0.1700
Data Index: 1653163 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9818. Min Act: -0.1700
Data Index: 4102621 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9505. Min Act: -0.1700
Data Index: 1119085 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9505. Min Act: -0.1700
Data Index: 8099420 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9818. Min Act: -0.1700
Data Index: 280977 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9505. Min Act: -0.1700
Data Index: 7787517 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9505. Min Act: -0.1700
Data Index: 1805736 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9505. Min Act: -0.1700
Data Index: 1322050 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6693. Min Range: -5.6693
Max Act: 4.9193. Min Act: -0.1700
Data Index: 6248461 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19