Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.3911. Min Act: -0.1700
Data Index: 8601751 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.3599. Min Act: -0.1700
Data Index: 8279194 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.2349. Min Act: -0.1700
Data Index: 2952254 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.1411. Min Act: -0.1700
Data Index: 3919565 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.1099. Min Act: -0.1700
Data Index: 3716371 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.1099. Min Act: -0.1700
Data Index: 8000512 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0474. Min Act: -0.1700
Data Index: 2444121 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 1451599 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0474. Min Act: -0.1700
Data Index: 6353673 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0474. Min Act: -0.1700
Data Index: 2344089 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0786. Min Act: -0.1700
Data Index: 3442758 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0161. Min Act: -0.1700
Data Index: 4824052 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3911. Min Range: -5.3911
Max Act: 5.0161. Min Act: -0.1700
Data Index: 4022330 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9849. Min Act: -0.1700
Data Index: 3461549 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9849. Min Act: -0.1700
Data Index: 7718947 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9849. Min Act: -0.1700
Data Index: 7797906 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9224. Min Act: -0.1700
Data Index: 5369937 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9224. Min Act: -0.1700
Data Index: 5371649 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9224. Min Act: -0.1700
Data Index: 521934 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3911. Min Range: -5.3911
Max Act: 4.9224. Min Act: -0.1700
Data Index: 3752505 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19