Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1525. Min Range: -6.1525
Max Act: 6.1525. Min Act: -0.1700
Data Index: 1318936 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8653727 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9962. Min Act: -0.1700
Data Index: 3426247 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9962. Min Act: -0.1700
Data Index: 7058707 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9650. Min Act: -0.1700
Data Index: 2895341 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9337. Min Act: -0.1700
Data Index: 343152 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9025. Min Act: -0.1700
Data Index: 3426246 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8712. Min Act: -0.1700
Data Index: 955359 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8712. Min Act: -0.1700
Data Index: 3016770 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.9025. Min Act: -0.1700
Data Index: 871136 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8712. Min Act: -0.1700
Data Index: 776452 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8087. Min Act: -0.1700
Data Index: 4422451 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8087. Min Act: -0.1700
Data Index: 1361223 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 8653726 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.8087. Min Act: -0.1700
Data Index: 161260 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 451244 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 1647422 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 7411003 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 6439553 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1525. Min Range: -6.1525
Max Act: 5.7775. Min Act: -0.1700
Data Index: 494402 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19