Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 600 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1714. Min Range: -4.1714
Max Act: 4.1714. Min Act: -0.1700
Data Index: 2497647 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1714. Min Range: -4.1714
Max Act: 4.0777. Min Act: -0.1700
Data Index: 6792309 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.9214. Min Act: -0.1700
Data Index: 3961272 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.9526. Min Act: -0.1700
Data Index: 3148462 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.9214. Min Act: -0.1700
Data Index: 7005189 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.9214. Min Act: -0.1700
Data Index: 3235571 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8901. Min Act: -0.1700
Data Index: 6490331 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8901. Min Act: -0.1700
Data Index: 1825156 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8588. Min Act: -0.1700
Data Index: 2943385 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8901. Min Act: -0.1700
Data Index: 4169794 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1834323 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8276. Min Act: -0.1700
Data Index: 1081302 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8588. Min Act: -0.1700
Data Index: 3134924 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8276. Min Act: -0.1700
Data Index: 1435775 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8276. Min Act: -0.1700
Data Index: 510749 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.8276. Min Act: -0.1700
Data Index: 1114640 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.7963. Min Act: -0.1700
Data Index: 4187579 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.7650. Min Act: -0.1700
Data Index: 1198719 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.7963. Min Act: -0.1700
Data Index: 4548443 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1714. Min Range: -4.1714
Max Act: 3.7963. Min Act: -0.1700
Data Index: 4797683 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19