Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5379 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.4988. Min Act: -0.1700
Data Index: 8755455 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.4676. Min Act: -0.1700
Data Index: 2557071 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.3426. Min Act: -0.1700
Data Index: 964175 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.2488. Min Act: -0.1700
Data Index: 2664720 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.2176. Min Act: -0.1700
Data Index: 8165793 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.1238. Min Act: -0.1700
Data Index: 1963359 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7390065 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7952 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.0301. Min Act: -0.1700
Data Index: 1036990 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4988. Min Range: -6.4988
Max Act: 6.0301. Min Act: -0.1700
Data Index: 545125 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9676. Min Act: -0.1700
Data Index: 1002181 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 6045035 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 4211180 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9676. Min Act: -0.1700
Data Index: 7373016 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9676. Min Act: -0.1700
Data Index: 1174313 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 6714736 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 5856015 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 3081006 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9363. Min Act: -0.1700
Data Index: 1978948 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4988. Min Range: -6.4988
Max Act: 5.9051. Min Act: -0.1700
Data Index: 349060 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19