Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.6457. Min Act: -0.1700
Data Index: 4480567 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.6770. Min Act: -0.1700
Data Index: 4406677 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4895. Min Act: -0.1700
Data Index: 4048101 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4582. Min Act: -0.1700
Data Index: 5300811 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4582. Min Act: -0.1700
Data Index: 4490629 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7870431 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3332. Min Act: -0.1700
Data Index: 3567694 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3020. Min Act: -0.1700
Data Index: 5241063 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.2707. Min Act: -0.1700
Data Index: 4325414 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.2395. Min Act: -0.1700
Data Index: 7574924 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7086563 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 727613 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7032341 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5861018 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 3276546 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1770. Min Act: -0.1700
Data Index: 83007 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1457. Min Act: -0.1700
Data Index: 8826733 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1145. Min Act: -0.1700
Data Index: 3654764 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1145. Min Act: -0.1700
Data Index: 2259079 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.1145. Min Act: -0.1700
Data Index: 1820066 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19