Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5854 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.4506. Min Act: -0.1700
Data Index: 6291867 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.2943. Min Act: -0.1700
Data Index: 3013600 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.2631. Min Act: -0.1700
Data Index: 2975472 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.2318. Min Act: -0.1700
Data Index: 2975486 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.2006. Min Act: -0.1700
Data Index: 2189942 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.1693. Min Act: -0.1700
Data Index: 2061234 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.1693. Min Act: -0.1700
Data Index: 7729075 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.0443. Min Act: -0.1700
Data Index: 3920880 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.0131. Min Act: -0.1700
Data Index: 1651799 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 4700021 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4506. Min Range: -6.4506
Max Act: 6.0131. Min Act: -0.1700
Data Index: 4368414 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 3899646 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 7873907 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 4377063 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 5330450 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9818. Min Act: -0.1700
Data Index: 7574972 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 5678387 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 8715700 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 3155759 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4506. Min Range: -6.4506
Max Act: 5.8881. Min Act: -0.1700
Data Index: 6560183 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19