Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.8561. Min Act: -0.1700
Data Index: 3418624 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6998. Min Act: -0.1700
Data Index: 431347 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6686. Min Act: -0.1700
Data Index: 3713884 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6686. Min Act: -0.1700
Data Index: 2963153 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6998. Min Act: -0.1700
Data Index: 6467048 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6686. Min Act: -0.1700
Data Index: 2561784 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.6686. Min Act: -0.1700
Data Index: 400479 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5748. Min Act: -0.1700
Data Index: 6475143 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5436. Min Act: -0.1700
Data Index: 5335627 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5436. Min Act: -0.1700
Data Index: 5279700 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5436. Min Act: -0.1700
Data Index: 4055239 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5123. Min Act: -0.1700
Data Index: 3418622 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.5123. Min Act: -0.1700
Data Index: 7878198 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4811. Min Act: -0.1700
Data Index: 6467047 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4811. Min Act: -0.1700
Data Index: 1181297 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4811. Min Act: -0.1700
Data Index: 6129660 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4811. Min Act: -0.1700
Data Index: 2406988 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4186. Min Act: -0.1700
Data Index: 918423 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.4186. Min Act: -0.1700
Data Index: 4396607 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8561. Min Range: -7.8561
Max Act: 7.3873. Min Act: -0.1700
Data Index: 1663357 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19