Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.8614. Min Act: -0.1700
Data Index: 1718177 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.7364. Min Act: -0.1700
Data Index: 2058806 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.5489. Min Act: -0.1700
Data Index: 6359163 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.6114. Min Act: -0.1700
Data Index: 7593542 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.5489. Min Act: -0.1700
Data Index: 5162158 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.5489. Min Act: -0.1700
Data Index: 6856194 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.6114. Min Act: -0.1700
Data Index: 7300265 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.4864. Min Act: -0.1700
Data Index: 1036173 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.4239. Min Act: -0.1700
Data Index: 3325686 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.4239. Min Act: -0.1700
Data Index: 6564931 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.3614. Min Act: -0.1700
Data Index: 4001879 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.3614. Min Act: -0.1700
Data Index: 7776106 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.3614. Min Act: -0.1700
Data Index: 4156692 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2989. Min Act: -0.1700
Data Index: 2177623 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2989. Min Act: -0.1700
Data Index: 8429608 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2989. Min Act: -0.1700
Data Index: 7286327 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.1739. Min Act: -0.1700
Data Index: 2334805 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2364. Min Act: -0.1700
Data Index: 4812026 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2364. Min Act: -0.1700
Data Index: 982147 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8614. Min Range: -9.8614
Max Act: 9.2364. Min Act: -0.1700
Data Index: 170144 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19