Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5997. Min Range: -12.5997
Max Act: 12.5997. Min Act: -0.1700
Data Index: 93834 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5997. Min Range: -12.5997
Max Act: 12.1622. Min Act: -0.1700
Data Index: 8207251 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5997. Min Range: -12.5997
Max Act: 12.0997. Min Act: -0.1700
Data Index: 3238806 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.9122. Min Act: -0.1700
Data Index: 3445157 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.8497. Min Act: -0.1700
Data Index: 970364 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.8497. Min Act: -0.1700
Data Index: 2827642 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.7247. Min Act: -0.1700
Data Index: 8756239 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.4747. Min Act: -0.1700
Data Index: 1381499 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.4747. Min Act: -0.1700
Data Index: 2736691 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.4747. Min Act: -0.1700
Data Index: 8674404 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.4122. Min Act: -0.1700
Data Index: 5397111 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.3497. Min Act: -0.1700
Data Index: 2294273 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.3497. Min Act: -0.1700
Data Index: 3080007 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.3497. Min Act: -0.1700
Data Index: 4809593 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2872. Min Act: -0.1700
Data Index: 4927431 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2872. Min Act: -0.1700
Data Index: 5848883 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2247. Min Act: -0.1700
Data Index: 7510108 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2872. Min Act: -0.1700
Data Index: 3681294 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2872. Min Act: -0.1700
Data Index: 1339814 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5997. Min Range: -12.5997
Max Act: 11.2247. Min Act: -0.1700
Data Index: 1879225 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19