Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.4934. Min Act: -0.1700
Data Index: 1731503 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.3684. Min Act: -0.1700
Data Index: 2068998 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.2434. Min Act: -0.1700
Data Index: 7257116 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.2434. Min Act: -0.1700
Data Index: 3979043 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.2121. Min Act: -0.1700
Data Index: 8399517 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.1496. Min Act: -0.1700
Data Index: 1145801 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.1184. Min Act: -0.1700
Data Index: 33673 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.1184. Min Act: -0.1700
Data Index: 8470687 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.1184. Min Act: -0.1700
Data Index: 931547 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0871. Min Act: -0.1700
Data Index: 6810167 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0871. Min Act: -0.1700
Data Index: 8313434 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0871. Min Act: -0.1700
Data Index: 8491122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0559. Min Act: -0.1700
Data Index: 4156471 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3966416 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3033174 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 2098302 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 771948 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 6312814 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3566235 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4934. Min Range: -5.4934
Max Act: 5.0246. Min Act: -0.1700
Data Index: 2617131 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19