Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1390. Min Range: -7.1390
Max Act: 7.1390. Min Act: -0.1700
Data Index: 6408035 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1390. Min Range: -7.1390
Max Act: 7.1390. Min Act: -0.1700
Data Index: 6893292 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1390. Min Range: -7.1390
Max Act: 7.1077. Min Act: -0.1700
Data Index: 1293739 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1390. Min Range: -7.1390
Max Act: 7.0452. Min Act: -0.1700
Data Index: 6475189 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.8577. Min Act: -0.1700
Data Index: 1905363 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7952. Min Act: -0.1700
Data Index: 4029110 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7952. Min Act: -0.1700
Data Index: 8633543 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7640. Min Act: -0.1700
Data Index: 8411792 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7015. Min Act: -0.1700
Data Index: 3934691 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7327. Min Act: -0.1700
Data Index: 7390925 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.7015. Min Act: -0.1700
Data Index: 7486593 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.6702. Min Act: -0.1700
Data Index: 5722610 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5765. Min Act: -0.1700
Data Index: 893208 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5765. Min Act: -0.1700
Data Index: 3417816 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5452. Min Act: -0.1700
Data Index: 5335578 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5452. Min Act: -0.1700
Data Index: 128393 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5452. Min Act: -0.1700
Data Index: 6338192 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5765. Min Act: -0.1700
Data Index: 7151722 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5140. Min Act: -0.1700
Data Index: 6484576 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1390. Min Range: -7.1390
Max Act: 6.5140. Min Act: -0.1700
Data Index: 577108 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19