Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0729. Min Act: -0.1700
Data Index: 5171977 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0416. Min Act: -0.1700
Data Index: 1453425 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0416. Min Act: -0.1700
Data Index: 642894 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0104. Min Act: -0.1700
Data Index: 6608508 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2714423 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2760721 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.9166. Min Act: -0.1700
Data Index: 898773 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.8541. Min Act: -0.1700
Data Index: 4913307 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.8229. Min Act: -0.1700
Data Index: 7800312 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.8229. Min Act: -0.1700
Data Index: 4803857 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.8229. Min Act: -0.1700
Data Index: 989644 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7916. Min Act: -0.1700
Data Index: 6235038 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7916. Min Act: -0.1700
Data Index: 351858 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7916. Min Act: -0.1700
Data Index: 3747824 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7604. Min Act: -0.1700
Data Index: 7997316 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7604. Min Act: -0.1700
Data Index: 1245299 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7604. Min Act: -0.1700
Data Index: 4873233 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7916. Min Act: -0.1700
Data Index: 717181 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7604. Min Act: -0.1700
Data Index: 2499815 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7291. Min Act: -0.1700
Data Index: 5405201 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19