Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.3549. Min Act: -0.1700
Data Index: 2501163 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.2924. Min Act: -0.1700
Data Index: 6682736 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.2924. Min Act: -0.1700
Data Index: 3545723 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.2299. Min Act: -0.1700
Data Index: 518475 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.2299. Min Act: -0.1700
Data Index: 931712 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.1049. Min Act: -0.1700
Data Index: 509845 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.1674. Min Act: -0.1700
Data Index: 699910 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3549. Min Range: -8.3549
Max Act: 8.0424. Min Act: -0.1700
Data Index: 4844448 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9799. Min Act: -0.1700
Data Index: 4655251 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9799. Min Act: -0.1700
Data Index: 8427811 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9799. Min Act: -0.1700
Data Index: 4316021 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9799. Min Act: -0.1700
Data Index: 417823 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9486. Min Act: -0.1700
Data Index: 7761822 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9799. Min Act: -0.1700
Data Index: 1189116 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9486. Min Act: -0.1700
Data Index: 1150522 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9486. Min Act: -0.1700
Data Index: 8057316 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.9174. Min Act: -0.1700
Data Index: 2875687 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.8861. Min Act: -0.1700
Data Index: 4746748 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.8549. Min Act: -0.1700
Data Index: 8788952 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3549. Min Range: -8.3549
Max Act: 7.8549. Min Act: -0.1700
Data Index: 3076005 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19