Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4284. Min Range: -9.4284
Max Act: 9.4284. Min Act: -0.1700
Data Index: 3139255 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4284. Min Range: -9.4284
Max Act: 9.1784. Min Act: -0.1700
Data Index: 2950569 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4284. Min Range: -9.4284
Max Act: 9.1784. Min Act: -0.1700
Data Index: 3400016 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.9909. Min Act: -0.1700
Data Index: 1585238 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.7409. Min Act: -0.1700
Data Index: 7527862 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.5534. Min Act: -0.1700
Data Index: 4849612 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.4909. Min Act: -0.1700
Data Index: 3899200 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.4284. Min Act: -0.1700
Data Index: 5898808 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.3659. Min Act: -0.1700
Data Index: 5038049 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.4284. Min Act: -0.1700
Data Index: 127301 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.3034. Min Act: -0.1700
Data Index: 6911898 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.3034. Min Act: -0.1700
Data Index: 6999322 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.2409. Min Act: -0.1700
Data Index: 4256877 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.2409. Min Act: -0.1700
Data Index: 7544050 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.1784. Min Act: -0.1700
Data Index: 5968905 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.1784. Min Act: -0.1700
Data Index: 8123120 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.1159. Min Act: -0.1700
Data Index: 8398800 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.1159. Min Act: -0.1700
Data Index: 8123119 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4284. Min Range: -9.4284
Max Act: 8.0534. Min Act: -0.1700
Data Index: 8064917 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4284. Min Range: -9.4284
Max Act: 7.9909. Min Act: -0.1700
Data Index: 1376969 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19