Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.7881. Min Act: -0.1700
Data Index: 6586973 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.7256. Min Act: -0.1700
Data Index: 3181023 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.6006. Min Act: -0.1700
Data Index: 4528757 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.5068. Min Act: -0.1700
Data Index: 1582359 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.4443. Min Act: -0.1700
Data Index: 5514497 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.4131. Min Act: -0.1700
Data Index: 7245807 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.4131. Min Act: -0.1700
Data Index: 2634223 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.4131. Min Act: -0.1700
Data Index: 2643511 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3818. Min Act: -0.1700
Data Index: 551179 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3506. Min Act: -0.1700
Data Index: 5514496 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3506. Min Act: -0.1700
Data Index: 1841344 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3818. Min Act: -0.1700
Data Index: 7175288 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3193. Min Act: -0.1700
Data Index: 1327815 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3506. Min Act: -0.1700
Data Index: 2176135 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.2881. Min Act: -0.1700
Data Index: 2081551 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.3193. Min Act: -0.1700
Data Index: 775869 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.2568. Min Act: -0.1700
Data Index: 2130325 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.1943. Min Act: -0.1700
Data Index: 2913737 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.1631. Min Act: -0.1700
Data Index: 6431426 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7881. Min Range: -5.7881
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3428655 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19