Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 1999057 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 2071096 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5644. Min Act: -0.1700
Data Index: 1672574 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5019. Min Act: -0.1700
Data Index: 6529405 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5019. Min Act: -0.1700
Data Index: 2024163 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 6916735 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 7367596 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3769. Min Act: -0.1700
Data Index: 4551427 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 3879208 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3769. Min Act: -0.1700
Data Index: 4953985 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 4384159 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3457. Min Act: -0.1700
Data Index: 1335361 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 5070453 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 4065007 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 6335273 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 827260 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.2831. Min Act: -0.1700
Data Index: 8066733 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.2831. Min Act: -0.1700
Data Index: 2024162 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.2831. Min Act: -0.1700
Data Index: 6423186 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.2831. Min Act: -0.1700
Data Index: 3197250 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19