Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.9068. Min Act: -0.1700
Data Index: 909660 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8898. Min Act: -0.1700
Data Index: 2205581 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8641. Min Act: -0.1700
Data Index: 6960874 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8641. Min Act: -0.1700
Data Index: 8375680 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8299. Min Act: -0.1700
Data Index: 4415915 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8470. Min Act: -0.1700
Data Index: 7406019 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8127. Min Act: -0.1700
Data Index: 2020593 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 8575847 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8127. Min Act: -0.1700
Data Index: 7341833 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8127. Min Act: -0.1700
Data Index: 8082749 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 3086619 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 3086614 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7955. Min Act: -0.1700
Data Index: 1402718 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7955. Min Act: -0.1700
Data Index: 4191835 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7869. Min Act: -0.1700
Data Index: 2996856 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7783. Min Act: -0.1700
Data Index: 194798 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7869. Min Act: -0.1700
Data Index: 5776897 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7869. Min Act: -0.1700
Data Index: 6071697 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7783. Min Act: -0.1700
Data Index: 5465464 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7783. Min Act: -0.1700
Data Index: 5058105 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19