Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4947 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.8242. Min Act: -0.1700
Data Index: 7655541 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.6992. Min Act: -0.1700
Data Index: 2029385 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.7305. Min Act: -0.1700
Data Index: 2473749 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.6367. Min Act: -0.1700
Data Index: 1411054 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.3867. Min Act: -0.1700
Data Index: 1411052 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.2617. Min Act: -0.1700
Data Index: 5219928 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.1680. Min Act: -0.1700
Data Index: 4315965 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.1680. Min Act: -0.1700
Data Index: 8698077 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.1367. Min Act: -0.1700
Data Index: 8821425 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.1055. Min Act: -0.1700
Data Index: 3222937 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.0742. Min Act: -0.1700
Data Index: 7200165 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8242. Min Range: -7.8242
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3346542 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9805. Min Act: -0.1700
Data Index: 3863538 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 2175954 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9805. Min Act: -0.1700
Data Index: 93180 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9805. Min Act: -0.1700
Data Index: 5309093 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 1663504 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9492. Min Act: -0.1700
Data Index: 183372 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9180. Min Act: -0.1700
Data Index: 3526666 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8242. Min Range: -7.8242
Max Act: 6.9180. Min Act: -0.1700
Data Index: 5003943 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19