Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2513 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0456. Min Range: -6.0456
Max Act: 6.0456. Min Act: -0.1700
Data Index: 292653 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.9831. Min Act: -0.1700
Data Index: 3225935 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0456. Min Range: -6.0456
Max Act: 6.0143. Min Act: -0.1700
Data Index: 5956369 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.9831. Min Act: -0.1700
Data Index: 1314298 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5619413 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.9206. Min Act: -0.1700
Data Index: 6416902 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8893. Min Act: -0.1700
Data Index: 473661 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8581. Min Act: -0.1700
Data Index: 3506723 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8581. Min Act: -0.1700
Data Index: 4486565 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8268. Min Act: -0.1700
Data Index: 8120900 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8268. Min Act: -0.1700
Data Index: 3982857 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8268. Min Act: -0.1700
Data Index: 707451 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8268. Min Act: -0.1700
Data Index: 7236656 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.8268. Min Act: -0.1700
Data Index: 7125786 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7643. Min Act: -0.1700
Data Index: 6997203 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7956. Min Act: -0.1700
Data Index: 1379812 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7643. Min Act: -0.1700
Data Index: 2465288 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7643. Min Act: -0.1700
Data Index: 3260513 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7643. Min Act: -0.1700
Data Index: 7145240 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0456. Min Range: -6.0456
Max Act: 5.7331. Min Act: -0.1700
Data Index: 6282154 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19