Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2262 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.9937. Min Act: -0.1700
Data Index: 5662909 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.8062. Min Act: -0.1700
Data Index: 5756534 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.7437. Min Act: -0.1700
Data Index: 4092895 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4937. Min Act: -0.1700
Data Index: 166741 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.5562. Min Act: -0.1700
Data Index: 2616513 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4937. Min Act: -0.1700
Data Index: 1775226 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4937. Min Act: -0.1700
Data Index: 3638223 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4937. Min Act: -0.1700
Data Index: 6056864 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4312. Min Act: -0.1700
Data Index: 7212215 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4312. Min Act: -0.1700
Data Index: 3638216 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 7573945 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 215547 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.4312. Min Act: -0.1700
Data Index: 4818866 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 6806193 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 2120668 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 6673724 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 2023396 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 3427778 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 5134823 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9937. Min Range: -8.9937
Max Act: 8.3687. Min Act: -0.1700
Data Index: 3018059 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19