Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.3846. Min Act: -0.1700
Data Index: 8452743 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.4471. Min Act: -0.1700
Data Index: 5084508 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.3846. Min Act: -0.1700
Data Index: 8267189 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.1346. Min Act: -0.1700
Data Index: 4560582 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.1346. Min Act: -0.1700
Data Index: 3645071 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.1034. Min Act: -0.1700
Data Index: 3694732 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.0721. Min Act: -0.1700
Data Index: 3536512 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.0721. Min Act: -0.1700
Data Index: 423929 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4471. Min Range: -8.4471
Max Act: 8.0096. Min Act: -0.1700
Data Index: 7312190 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9784. Min Act: -0.1700
Data Index: 1200483 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9471. Min Act: -0.1700
Data Index: 4724744 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9159. Min Act: -0.1700
Data Index: 1906915 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9159. Min Act: -0.1700
Data Index: 4959169 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9159. Min Act: -0.1700
Data Index: 3518007 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9159. Min Act: -0.1700
Data Index: 3611095 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.9159. Min Act: -0.1700
Data Index: 3474276 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.8846. Min Act: -0.1700
Data Index: 5660626 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.8846. Min Act: -0.1700
Data Index: 5304120 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.8846. Min Act: -0.1700
Data Index: 878636 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4471. Min Range: -8.4471
Max Act: 7.8534. Min Act: -0.1700
Data Index: 2391242 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19