Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8660. Min Act: -0.1700
Data Index: 2411717 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 6010285 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 7649377 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8660. Min Act: -0.1700
Data Index: 7862895 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8660. Min Act: -0.1700
Data Index: 8217729 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8660. Min Act: -0.1700
Data Index: 164108 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 45089 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 44157 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 42307 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 36850 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 36622 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 31585 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 31137 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8035. Min Act: -0.1700
Data Index: 28172 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 22840 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 20901 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 20589 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 17680 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 14267 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8660. Min Range: -6.8660
Max Act: 6.8347. Min Act: -0.1700
Data Index: 13443 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19