Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3057. Min Range: -5.3057
Max Act: 5.3057. Min Act: -0.1700
Data Index: 7008890 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8994. Min Act: -0.1700
Data Index: 5074561 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8994. Min Act: -0.1700
Data Index: 8312637 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8682. Min Act: -0.1700
Data Index: 5038924 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8682. Min Act: -0.1700
Data Index: 5538507 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8369. Min Act: -0.1700
Data Index: 6729111 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8369. Min Act: -0.1700
Data Index: 5976130 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8057. Min Act: -0.1700
Data Index: 3915959 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7744. Min Act: -0.1700
Data Index: 2662967 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.8057. Min Act: -0.1700
Data Index: 3886287 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7432. Min Act: -0.1700
Data Index: 8356288 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7119. Min Act: -0.1700
Data Index: 8657496 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7119. Min Act: -0.1700
Data Index: 30592 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7119. Min Act: -0.1700
Data Index: 631438 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7119. Min Act: -0.1700
Data Index: 5892033 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.7119. Min Act: -0.1700
Data Index: 5359397 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.6807. Min Act: -0.1700
Data Index: 5960434 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.6182. Min Act: -0.1700
Data Index: 1067513 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.6494. Min Act: -0.1700
Data Index: 5220959 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3057. Min Range: -5.3057
Max Act: 4.6494. Min Act: -0.1700
Data Index: 6738619 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19