Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0092. Min Range: -1.0092
Max Act: 1.0092. Min Act: -0.1699
Data Index: 5033358 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.9745. Min Act: -0.1693
Data Index: 1062952 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.9056. Min Act: -0.1699
Data Index: 3024139 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8460. Min Act: -0.1700
Data Index: 4017173 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8291. Min Act: -0.1700
Data Index: 7427250 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8122. Min Act: -0.1696
Data Index: 2360133 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8207. Min Act: -0.1677
Data Index: 4620263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8038. Min Act: -0.1700
Data Index: 553456 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8038. Min Act: -0.1700
Data Index: 7340013 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.8038. Min Act: -0.1700
Data Index: 3024126 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7871. Min Act: -0.1699
Data Index: 2044400 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7955. Min Act: -0.1699
Data Index: 7556554 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7871. Min Act: -0.1700
Data Index: 5881791 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7704. Min Act: -0.1700
Data Index: 1961211 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7704. Min Act: -0.1700
Data Index: 4863177 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7704. Min Act: -0.1700
Data Index: 6796065 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7704. Min Act: -0.1700
Data Index: 6932741 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7538. Min Act: -0.1697
Data Index: 7465283 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7455. Min Act: -0.1698
Data Index: 8036264 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0092. Min Range: -1.0092
Max Act: 0.7455. Min Act: -0.1700
Data Index: 6556466 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19