Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.4465. Min Act: -0.1700
Data Index: 7284520 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.2590. Min Act: -0.1700
Data Index: 4400222 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3320330 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1653. Min Act: -0.1700
Data Index: 6822275 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1653. Min Act: -0.1700
Data Index: 5695548 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1340. Min Act: -0.1700
Data Index: 5456245 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1340. Min Act: -0.1700
Data Index: 3189266 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6091746 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6086802 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1028. Min Act: -0.1700
Data Index: 1661091 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.1028. Min Act: -0.1700
Data Index: 7693922 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7525936 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0715. Min Act: -0.1700
Data Index: 5896568 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0715. Min Act: -0.1700
Data Index: 309693 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 7748218 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 226449 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 7272420 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 7691982 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 2560884 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4465. Min Range: -5.4465
Max Act: 5.0403. Min Act: -0.1700
Data Index: 7220201 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19