Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5856 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3559. Min Act: -0.1700
Data Index: 8109684 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6068955 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6506583 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1997. Min Act: -0.1700
Data Index: 942093 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1997. Min Act: -0.1700
Data Index: 7282717 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1684. Min Act: -0.1700
Data Index: 749091 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1059. Min Act: -0.1700
Data Index: 6981552 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1059. Min Act: -0.1700
Data Index: 4426072 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0746. Min Act: -0.1700
Data Index: 5190784 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0746. Min Act: -0.1700
Data Index: 3510114 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0434. Min Act: -0.1700
Data Index: 3054462 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0434. Min Act: -0.1700
Data Index: 2726326 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0434. Min Act: -0.1700
Data Index: 6207343 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 4012962 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 5651068 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 1779945 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 1659292 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 5921363 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 1795729 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.0121. Min Act: -0.1700
Data Index: 8302676 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19