Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.9862. Min Act: -0.1700
Data Index: 7911740 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4287981 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.9549. Min Act: -0.1700
Data Index: 7406530 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.9237. Min Act: -0.1700
Data Index: 1801077 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.8924. Min Act: -0.1700
Data Index: 310368 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.8612. Min Act: -0.1700
Data Index: 1241968 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7987. Min Act: -0.1700
Data Index: 3793112 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.8299. Min Act: -0.1700
Data Index: 2614912 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.8612. Min Act: -0.1700
Data Index: 7469073 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7987. Min Act: -0.1700
Data Index: 4602981 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7987. Min Act: -0.1700
Data Index: 4648692 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7362. Min Act: -0.1700
Data Index: 6250181 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1239303 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1794293 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1999307 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 3575155 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1298177 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 2106199 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 3850674 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9862. Min Range: -4.9862
Max Act: 4.7049. Min Act: -0.1700
Data Index: 4568019 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19