Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.5838. Min Act: -0.1700
Data Index: 4786797 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.5525. Min Act: -0.1700
Data Index: 105985 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.5212. Min Act: -0.1700
Data Index: 5696748 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.5055. Min Act: -0.1700
Data Index: 7746961 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.5055. Min Act: -0.1700
Data Index: 3588445 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.4898. Min Act: -0.1700
Data Index: 105980 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.4742. Min Act: -0.1700
Data Index: 1002228 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.4585. Min Act: -0.1700
Data Index: 4090524 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.4115. Min Act: -0.1700
Data Index: 724296 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.3644. Min Act: -0.1700
Data Index: 4358862 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.3488. Min Act: -0.1700
Data Index: 2966972 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.3331. Min Act: -0.1700
Data Index: 8700892 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.3017. Min Act: -0.1700
Data Index: 337510 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.3017. Min Act: -0.1700
Data Index: 6534280 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2860. Min Act: -0.1700
Data Index: 6534279 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2703. Min Act: -0.1700
Data Index: 2966975 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2860. Min Act: -0.1700
Data Index: 3032909 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2389. Min Act: -0.1700
Data Index: 7468152 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2389. Min Act: -0.1700
Data Index: 6557009 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5838. Min Range: -3.5838
Max Act: 3.2389. Min Act: -0.1700
Data Index: 103651 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19