Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.5025. Min Range: -10.5025
Max Act: 10.5025. Min Act: -0.1700
Data Index: 2710250 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5025. Min Range: -10.5025
Max Act: 10.3150. Min Act: -0.1700
Data Index: 471424 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5025. Min Range: -10.5025
Max Act: 10.3775. Min Act: -0.1700
Data Index: 8552340 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5025. Min Range: -10.5025
Max Act: 10.0025. Min Act: -0.1700
Data Index: 3948191 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5025. Min Range: -10.5025
Max Act: 10.0025. Min Act: -0.1700
Data Index: 5944874 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.9400. Min Act: -0.1700
Data Index: 1005179 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.8150. Min Act: -0.1700
Data Index: 7851554 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.8150. Min Act: -0.1700
Data Index: 6564728 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.7525. Min Act: -0.1700
Data Index: 4570854 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6900. Min Act: -0.1700
Data Index: 2609815 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6900. Min Act: -0.1700
Data Index: 5502508 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6900. Min Act: -0.1700
Data Index: 6676970 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6900. Min Act: -0.1700
Data Index: 1583732 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.7525. Min Act: -0.1700
Data Index: 6636515 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6275. Min Act: -0.1700
Data Index: 1213453 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6275. Min Act: -0.1700
Data Index: 2199280 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6275. Min Act: -0.1700
Data Index: 1491603 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6900. Min Act: -0.1700
Data Index: 6506043 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.6275. Min Act: -0.1700
Data Index: 3503090 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5025. Min Range: -10.5025
Max Act: 9.5025. Min Act: -0.1700
Data Index: 6138275 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19