Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.5680. Min Act: -0.1700
Data Index: 6542641 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.2867. Min Act: -0.1700
Data Index: 7112346 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.1617. Min Act: -0.1700
Data Index: 1873105 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.1305. Min Act: -0.1700
Data Index: 7879704 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.1305. Min Act: -0.1700
Data Index: 4765281 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.0680. Min Act: -0.1700
Data Index: 771284 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.0680. Min Act: -0.1700
Data Index: 1370712 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.0367. Min Act: -0.1700
Data Index: 7611688 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.0055. Min Act: -0.1700
Data Index: 3293185 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9742. Min Act: -0.1700
Data Index: 3824617 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5680. Min Range: -7.5680
Max Act: 7.0055. Min Act: -0.1700
Data Index: 1121566 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9742. Min Act: -0.1700
Data Index: 5290154 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9742. Min Act: -0.1700
Data Index: 4416654 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9742. Min Act: -0.1700
Data Index: 1968457 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9430. Min Act: -0.1700
Data Index: 4817283 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9430. Min Act: -0.1700
Data Index: 3575703 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9117. Min Act: -0.1700
Data Index: 1823520 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9117. Min Act: -0.1700
Data Index: 7122399 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.9117. Min Act: -0.1700
Data Index: 2593304 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5680. Min Range: -7.5680
Max Act: 6.8805. Min Act: -0.1700
Data Index: 2612426 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19