Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1595. Min Range: -6.1595
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3323583 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1595. Min Range: -6.1595
Max Act: 6.0658. Min Act: -0.1700
Data Index: 1136554 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.8158. Min Act: -0.1700
Data Index: 8449895 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1530921 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 540712 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 7169411 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5970. Min Act: -0.1700
Data Index: 3700057 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5658. Min Act: -0.1700
Data Index: 2557787 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 8796556 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5817057 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2855880 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 8161818 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 3797810 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5033. Min Act: -0.1700
Data Index: 1314250 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5033. Min Act: -0.1700
Data Index: 4546604 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.4720. Min Act: -0.1700
Data Index: 7603330 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5033. Min Act: -0.1700
Data Index: 8082071 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.5033. Min Act: -0.1700
Data Index: 4032948 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.4720. Min Act: -0.1700
Data Index: 2464273 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1595. Min Range: -6.1595
Max Act: 5.4408. Min Act: -0.1700
Data Index: 7628766 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19