Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3073. Min Range: -4.3073
Max Act: 4.3073. Min Act: -0.1700
Data Index: 3926241 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3073. Min Range: -4.3073
Max Act: 4.0885. Min Act: -0.1700
Data Index: 661381 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.9322. Min Act: -0.1700
Data Index: 1691189 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.9166. Min Act: -0.1700
Data Index: 5927300 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8853. Min Act: -0.1700
Data Index: 7731005 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8853. Min Act: -0.1700
Data Index: 2403072 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8697. Min Act: -0.1700
Data Index: 3376728 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8697. Min Act: -0.1700
Data Index: 172273 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8540. Min Act: -0.1700
Data Index: 8651493 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8384. Min Act: -0.1700
Data Index: 6602554 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7915. Min Act: -0.1700
Data Index: 2336009 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.8071. Min Act: -0.1700
Data Index: 1376988 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7602. Min Act: -0.1700
Data Index: 7274534 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7602. Min Act: -0.1700
Data Index: 8079226 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7289. Min Act: -0.1700
Data Index: 257794 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7602. Min Act: -0.1700
Data Index: 280205 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7446. Min Act: -0.1700
Data Index: 1376989 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7446. Min Act: -0.1700
Data Index: 2942635 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7446. Min Act: -0.1700
Data Index: 3376733 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3073. Min Range: -4.3073
Max Act: 3.7289. Min Act: -0.1700
Data Index: 3535596 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19