Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1785 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5855. Min Act: -0.1700
Data Index: 351324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5855. Min Act: -0.1700
Data Index: 338646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 1380653 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 2039406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 2290434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 6914662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 2455278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 4730457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5542. Min Act: -0.1700
Data Index: 7237691 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 6957410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 406706 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 8024937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 7678525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 803646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 2585839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 5344248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 5162977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.5228. Min Act: -0.1700
Data Index: 1951770 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.4915. Min Act: -0.1700
Data Index: 1093480 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5855. Min Range: -3.5855
Max Act: 3.4915. Min Act: -0.1700
Data Index: 3008642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19