Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.7046. Min Act: -0.1700
Data Index: 6097352 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.5796. Min Act: -0.1700
Data Index: 1623546 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.5171. Min Act: -0.1700
Data Index: 6168248 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.5171. Min Act: -0.1700
Data Index: 2300652 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.4546. Min Act: -0.1700
Data Index: 8667340 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.4546. Min Act: -0.1700
Data Index: 6191905 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3921. Min Act: -0.1700
Data Index: 7127180 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3921. Min Act: -0.1700
Data Index: 3383690 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3921. Min Act: -0.1700
Data Index: 7946665 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3921. Min Act: -0.1700
Data Index: 6099343 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3921. Min Act: -0.1700
Data Index: 858193 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3296. Min Act: -0.1700
Data Index: 6403988 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3296. Min Act: -0.1700
Data Index: 2734126 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3296. Min Act: -0.1700
Data Index: 1264720 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.3296. Min Act: -0.1700
Data Index: 208870 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.2671. Min Act: -0.1700
Data Index: 613305 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.2671. Min Act: -0.1700
Data Index: 8728728 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.2046. Min Act: -0.1700
Data Index: 3899943 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.2046. Min Act: -0.1700
Data Index: 6609793 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7046. Min Range: -8.7046
Max Act: 8.2046. Min Act: -0.1700
Data Index: 5745100 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19