Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.5561. Min Act: -0.1700
Data Index: 2488608 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.4311. Min Act: -0.1700
Data Index: 1572674 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3686. Min Act: -0.1700
Data Index: 8523236 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3686. Min Act: -0.1700
Data Index: 8466102 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3686. Min Act: -0.1700
Data Index: 4773063 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3686. Min Act: -0.1700
Data Index: 2485880 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3374. Min Act: -0.1700
Data Index: 6486456 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3061. Min Act: -0.1700
Data Index: 4982613 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3061. Min Act: -0.1700
Data Index: 4129279 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2749. Min Act: -0.1700
Data Index: 4244882 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3061. Min Act: -0.1700
Data Index: 2053396 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.3061. Min Act: -0.1700
Data Index: 7790484 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2749. Min Act: -0.1700
Data Index: 8607561 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2749. Min Act: -0.1700
Data Index: 8725114 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2749. Min Act: -0.1700
Data Index: 3424499 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2124. Min Act: -0.1700
Data Index: 1051386 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2124. Min Act: -0.1700
Data Index: 8245553 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2124. Min Act: -0.1700
Data Index: 8340661 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2124. Min Act: -0.1700
Data Index: 6138941 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5561. Min Range: -5.5561
Max Act: 5.2124. Min Act: -0.1700
Data Index: 1308576 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19