Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.7904. Min Act: -0.1700
Data Index: 2427009 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.7279. Min Act: -0.1700
Data Index: 1675402 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.6029. Min Act: -0.1700
Data Index: 2946946 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.6029. Min Act: -0.1700
Data Index: 67064 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.6029. Min Act: -0.1700
Data Index: 6167897 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.5404. Min Act: -0.1700
Data Index: 5089720 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.4779. Min Act: -0.1700
Data Index: 3367232 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.5404. Min Act: -0.1700
Data Index: 6967877 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.5404. Min Act: -0.1700
Data Index: 2489240 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.4779. Min Act: -0.1700
Data Index: 7997072 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.4779. Min Act: -0.1700
Data Index: 6729631 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.4154. Min Act: -0.1700
Data Index: 4424357 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.4779. Min Act: -0.1700
Data Index: 2405961 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.3529. Min Act: -0.1700
Data Index: 683604 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.3529. Min Act: -0.1700
Data Index: 6167882 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.2591. Min Act: -0.1700
Data Index: 5853258 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.2279. Min Act: -0.1700
Data Index: 3473974 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.2591. Min Act: -0.1700
Data Index: 2715195 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.2591. Min Act: -0.1700
Data Index: 1051311 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7904. Min Range: -8.7904
Max Act: 8.1966. Min Act: -0.1700
Data Index: 4401509 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19