Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.9761. Min Act: -0.1700
Data Index: 6270339 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0074. Min Range: -6.0074
Max Act: 6.0074. Min Act: -0.1700
Data Index: 8578108 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.9761. Min Act: -0.1700
Data Index: 5018435 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.9761. Min Act: -0.1700
Data Index: 4635198 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.9136. Min Act: -0.1700
Data Index: 5112172 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.8199. Min Act: -0.1700
Data Index: 82532 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.7886. Min Act: -0.1700
Data Index: 4845232 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.7261. Min Act: -0.1700
Data Index: 6172783 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.6949. Min Act: -0.1700
Data Index: 7285191 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5982160 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2879378 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.6324. Min Act: -0.1700
Data Index: 468849 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.6324. Min Act: -0.1700
Data Index: 3395098 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5699. Min Act: -0.1700
Data Index: 8586703 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5699. Min Act: -0.1700
Data Index: 4332728 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5386. Min Act: -0.1700
Data Index: 16052 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5386. Min Act: -0.1700
Data Index: 8278201 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6541457 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5074. Min Act: -0.1700
Data Index: 7585920 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0074. Min Range: -6.0074
Max Act: 5.5074. Min Act: -0.1700
Data Index: 3072325 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19