Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3710. Min Range: -8.3710
Max Act: 8.3710. Min Act: -0.1700
Data Index: 6124052 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3710. Min Range: -8.3710
Max Act: 8.2772. Min Act: -0.1700
Data Index: 7850327 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3710. Min Range: -8.3710
Max Act: 8.0897. Min Act: -0.1700
Data Index: 146963 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3710. Min Range: -8.3710
Max Act: 8.0897. Min Act: -0.1700
Data Index: 6124049 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3710. Min Range: -8.3710
Max Act: 8.0272. Min Act: -0.1700
Data Index: 2435638 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.9647. Min Act: -0.1700
Data Index: 949990 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.8710. Min Act: -0.1700
Data Index: 7027669 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.8397. Min Act: -0.1700
Data Index: 432033 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.8085. Min Act: -0.1700
Data Index: 508995 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.8397. Min Act: -0.1700
Data Index: 1438760 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.7460. Min Act: -0.1700
Data Index: 4426257 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.7460. Min Act: -0.1700
Data Index: 5062142 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.7147. Min Act: -0.1700
Data Index: 2070708 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.6522. Min Act: -0.1700
Data Index: 5477249 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.6522. Min Act: -0.1700
Data Index: 2352131 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.6210. Min Act: -0.1700
Data Index: 2070709 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.5897. Min Act: -0.1700
Data Index: 2267954 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.5585. Min Act: -0.1700
Data Index: 1677192 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.5585. Min Act: -0.1700
Data Index: 3569754 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3710. Min Range: -8.3710
Max Act: 7.5272. Min Act: -0.1700
Data Index: 2166344 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19