Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.2145. Min Act: -0.1700
Data Index: 3936948 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0895. Min Act: -0.1700
Data Index: 2563617 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.1207. Min Act: -0.1700
Data Index: 3272559 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0895. Min Act: -0.1700
Data Index: 316275 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0895. Min Act: -0.1700
Data Index: 4653051 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0270. Min Act: -0.1700
Data Index: 4414633 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0270. Min Act: -0.1700
Data Index: 6669918 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2145. Min Range: -4.2145
Max Act: 4.0270. Min Act: -0.1700
Data Index: 4015246 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9957. Min Act: -0.1700
Data Index: 1858774 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9645. Min Act: -0.1700
Data Index: 8314945 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9332. Min Act: -0.1700
Data Index: 8626349 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9332. Min Act: -0.1700
Data Index: 1125709 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9332. Min Act: -0.1700
Data Index: 2048766 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9019. Min Act: -0.1700
Data Index: 6884300 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9019. Min Act: -0.1700
Data Index: 8113609 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9019. Min Act: -0.1700
Data Index: 6718729 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9019. Min Act: -0.1700
Data Index: 7317385 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.9019. Min Act: -0.1700
Data Index: 7155120 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.8707. Min Act: -0.1700
Data Index: 1171884 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2145. Min Range: -4.2145
Max Act: 3.8707. Min Act: -0.1700
Data Index: 7521886 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19