Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.9372. Min Act: -0.1700
Data Index: 5216988 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.9055. Min Act: -0.1700
Data Index: 7409757 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8738. Min Act: -0.1700
Data Index: 6838914 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8261. Min Act: -0.1700
Data Index: 7409753 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8261. Min Act: -0.1700
Data Index: 6378640 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8102. Min Act: -0.1700
Data Index: 5822765 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7943. Min Act: -0.1700
Data Index: 1392646 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8261. Min Act: -0.1700
Data Index: 311185 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7943. Min Act: -0.1700
Data Index: 6083159 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7943. Min Act: -0.1700
Data Index: 7409749 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.8102. Min Act: -0.1700
Data Index: 708090 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7305. Min Act: -0.1700
Data Index: 6765993 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7305. Min Act: -0.1700
Data Index: 2130919 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7305. Min Act: -0.1700
Data Index: 5381014 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7305. Min Act: -0.1700
Data Index: 5314723 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7305. Min Act: -0.1700
Data Index: 516238 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.6985. Min Act: -0.1700
Data Index: 723101 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7145. Min Act: -0.1700
Data Index: 529004 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7145. Min Act: -0.1700
Data Index: 4060370 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9372. Min Range: -2.9372
Max Act: 2.7145. Min Act: -0.1700
Data Index: 2249482 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19