Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.8160. Min Act: -0.1700
Data Index: 746297 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.8160. Min Act: -0.1700
Data Index: 2681105 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.7848. Min Act: -0.1700
Data Index: 4159428 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.7848. Min Act: -0.1700
Data Index: 70544 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.7535. Min Act: -0.1700
Data Index: 2133427 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6910. Min Act: -0.1700
Data Index: 1562291 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6910. Min Act: -0.1700
Data Index: 4229589 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6598. Min Act: -0.1700
Data Index: 822923 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.7223. Min Act: -0.1700
Data Index: 2629559 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6598. Min Act: -0.1700
Data Index: 2672551 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6285. Min Act: -0.1700
Data Index: 6079764 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6598. Min Act: -0.1700
Data Index: 8490727 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6285. Min Act: -0.1700
Data Index: 530545 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5973. Min Act: -0.1700
Data Index: 1170104 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.6285. Min Act: -0.1700
Data Index: 7703168 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6699785 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5660. Min Act: -0.1700
Data Index: 5584699 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5973. Min Act: -0.1700
Data Index: 2913680 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5973. Min Act: -0.1700
Data Index: 2884935 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5660. Min Act: -0.1700
Data Index: 1808212 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19