Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3009. Min Range: -6.3009
Max Act: 6.3009. Min Act: -0.1700
Data Index: 7556478 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3009. Min Range: -6.3009
Max Act: 6.1134. Min Act: -0.1700
Data Index: 3547640 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3009. Min Range: -6.3009
Max Act: 6.0197. Min Act: -0.1700
Data Index: 7331464 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.9884. Min Act: -0.1700
Data Index: 894566 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.9884. Min Act: -0.1700
Data Index: 3622285 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8634. Min Act: -0.1700
Data Index: 894567 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8947. Min Act: -0.1700
Data Index: 206353 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8947. Min Act: -0.1700
Data Index: 127890 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8634. Min Act: -0.1700
Data Index: 2235596 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8634. Min Act: -0.1700
Data Index: 6560790 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8322. Min Act: -0.1700
Data Index: 4608455 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7697. Min Act: -0.1700
Data Index: 8437386 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7697. Min Act: -0.1700
Data Index: 1723030 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.8009. Min Act: -0.1700
Data Index: 6119671 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7384. Min Act: -0.1700
Data Index: 2615093 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 8668821 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 8184059 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2438499 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 8673146 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3009. Min Range: -6.3009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 5439374 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19