Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.5879. Min Act: -0.1700
Data Index: 246887 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.5254. Min Act: -0.1700
Data Index: 4955348 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.3691. Min Act: -0.1700
Data Index: 4646044 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.2754. Min Act: -0.1700
Data Index: 2163616 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.2129. Min Act: -0.1700
Data Index: 526227 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.0879. Min Act: -0.1700
Data Index: 3880509 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.0566. Min Act: -0.1700
Data Index: 4956989 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.0254. Min Act: -0.1700
Data Index: 7504095 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9941. Min Act: -0.1700
Data Index: 5587332 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9941. Min Act: -0.1700
Data Index: 5394705 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 5007709 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9316. Min Act: -0.1700
Data Index: 5477123 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 4945401 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 960290 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 285582 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8691. Min Act: -0.1700
Data Index: 1700773 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8379. Min Act: -0.1700
Data Index: 4099510 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8379. Min Act: -0.1700
Data Index: 4091114 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8066. Min Act: -0.1700
Data Index: 3550292 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8379. Min Act: -0.1700
Data Index: 6171652 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19