Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.3058. Min Act: -0.1700
Data Index: 6125833 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.1808. Min Act: -0.1700
Data Index: 2435326 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.1183. Min Act: -0.1700
Data Index: 3338829 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.1183. Min Act: -0.1700
Data Index: 323452 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.0558. Min Act: -0.1700
Data Index: 5110916 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.1183. Min Act: -0.1700
Data Index: 7861417 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.0558. Min Act: -0.1700
Data Index: 7726454 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3058. Min Range: -8.3058
Max Act: 8.0558. Min Act: -0.1700
Data Index: 8087566 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9933. Min Act: -0.1700
Data Index: 4215055 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 6963611 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7217794 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7460423 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 2883379 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 6335489 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7943204 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7999684 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 8030070 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 1529887 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 3211079 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3058. Min Range: -8.3058
Max Act: 7.9308. Min Act: -0.1700
Data Index: 8039479 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19