Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.8525. Min Act: -0.1700
Data Index: 6137425 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.8212. Min Act: -0.1700
Data Index: 6774118 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.8212. Min Act: -0.1700
Data Index: 2531049 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.7275. Min Act: -0.1700
Data Index: 1675513 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.7587. Min Act: -0.1700
Data Index: 8482020 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.7587. Min Act: -0.1700
Data Index: 3153745 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.7275. Min Act: -0.1700
Data Index: 6774119 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.7275. Min Act: -0.1700
Data Index: 7947885 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.6650. Min Act: -0.1700
Data Index: 5440564 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.6337. Min Act: -0.1700
Data Index: 8622365 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.6025. Min Act: -0.1700
Data Index: 4807238 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.6337. Min Act: -0.1700
Data Index: 4614837 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5712. Min Act: -0.1700
Data Index: 1647093 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5712. Min Act: -0.1700
Data Index: 4160453 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5712. Min Act: -0.1700
Data Index: 2124339 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5400. Min Act: -0.1700
Data Index: 2359910 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5087. Min Act: -0.1700
Data Index: 7797363 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5400. Min Act: -0.1700
Data Index: 8174126 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5087. Min Act: -0.1700
Data Index: 5256887 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8525. Min Range: -6.8525
Max Act: 6.5087. Min Act: -0.1700
Data Index: 2677023 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19