Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5471 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5947. Min Range: -10.5947
Max Act: 10.5947. Min Act: -0.1700
Data Index: 6332521 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5947. Min Range: -10.5947
Max Act: 9.9697. Min Act: -0.1700
Data Index: 1616531 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5947. Min Range: -10.5947
Max Act: 9.5322. Min Act: -0.1700
Data Index: 3269151 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5947. Min Range: -10.5947
Max Act: 9.0947. Min Act: -0.1700
Data Index: 1653766 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5947. Min Range: -10.5947
Max Act: 9.0947. Min Act: -0.1700
Data Index: 6654292 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.8447. Min Act: -0.1700
Data Index: 1251755 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7822. Min Act: -0.1700
Data Index: 1019892 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7822. Min Act: -0.1700
Data Index: 3395866 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7822. Min Act: -0.1700
Data Index: 6384916 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.8447. Min Act: -0.1700
Data Index: 7296596 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7822. Min Act: -0.1700
Data Index: 3720724 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7197. Min Act: -0.1700
Data Index: 3851846 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.7197. Min Act: -0.1700
Data Index: 3602240 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.6572. Min Act: -0.1700
Data Index: 1889200 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.6572. Min Act: -0.1700
Data Index: 3851841 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.6572. Min Act: -0.1700
Data Index: 482790 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.5947. Min Act: -0.1700
Data Index: 1520195 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.5947. Min Act: -0.1700
Data Index: 5991016 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.5947. Min Act: -0.1700
Data Index: 1504900 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5947. Min Range: -10.5947
Max Act: 8.6572. Min Act: -0.1700
Data Index: 1553145 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19