Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 839 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.1729. Min Act: -0.1700
Data Index: 6083264 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7315498 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2858619 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9229. Min Act: -0.1700
Data Index: 6906684 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8604. Min Act: -0.1700
Data Index: 5743510 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8917. Min Act: -0.1700
Data Index: 3207688 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8604. Min Act: -0.1700
Data Index: 5767307 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8604. Min Act: -0.1700
Data Index: 7057424 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8763070 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1259970 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.7979. Min Act: -0.1700
Data Index: 1363903 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4918654 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.7042. Min Act: -0.1700
Data Index: 1107093 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.7042. Min Act: -0.1700
Data Index: 3680469 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 7634116 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8539441 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 6208892 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 4548166 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6417. Min Act: -0.1700
Data Index: 6195174 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 703282 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19