Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2118 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1305. Min Range: -6.1305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3150444 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.9743. Min Act: -0.1700
Data Index: 5768536 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1305. Min Range: -6.1305
Max Act: 6.0055. Min Act: -0.1700
Data Index: 2557551 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1195973 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1005909 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.9118. Min Act: -0.1700
Data Index: 7598170 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2784087 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.8493. Min Act: -0.1700
Data Index: 1875415 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7868. Min Act: -0.1700
Data Index: 6760559 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 3803661 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 1515791 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 633311 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 4827873 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 5305553 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7243. Min Act: -0.1700
Data Index: 1816803 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 7755252 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 5407351 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 7886836 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7555. Min Act: -0.1700
Data Index: 2663623 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1305. Min Range: -6.1305
Max Act: 5.7243. Min Act: -0.1700
Data Index: 701285 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19