Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4556 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0051. Min Range: -8.0051
Max Act: 8.0051. Min Act: -0.1700
Data Index: 6982970 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0051. Min Range: -8.0051
Max Act: 8.0051. Min Act: -0.1700
Data Index: 5671857 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.8801. Min Act: -0.1700
Data Index: 4183733 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.8176. Min Act: -0.1700
Data Index: 8264218 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.6301. Min Act: -0.1700
Data Index: 158552 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.5676. Min Act: -0.1700
Data Index: 2858769 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.5364. Min Act: -0.1700
Data Index: 7085576 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.5676. Min Act: -0.1700
Data Index: 966104 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.4739. Min Act: -0.1700
Data Index: 2438388 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.4426. Min Act: -0.1700
Data Index: 7181187 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.4739. Min Act: -0.1700
Data Index: 1061482 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3801. Min Act: -0.1700
Data Index: 3710317 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.4114. Min Act: -0.1700
Data Index: 544930 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.4114. Min Act: -0.1700
Data Index: 4217454 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3489. Min Act: -0.1700
Data Index: 7773391 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3489. Min Act: -0.1700
Data Index: 2281428 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3489. Min Act: -0.1700
Data Index: 3096320 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3176. Min Act: -0.1700
Data Index: 300228 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.3176. Min Act: -0.1700
Data Index: 8759911 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0051. Min Range: -8.0051
Max Act: 7.2864. Min Act: -0.1700
Data Index: 6196171 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19