Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0309. Min Range: -7.0309
Max Act: 7.0309. Min Act: -0.1700
Data Index: 3114418 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.9059. Min Act: -0.1700
Data Index: 3893886 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.6559. Min Act: -0.1700
Data Index: 3033079 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.4372. Min Act: -0.1700
Data Index: 7508772 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.3434. Min Act: -0.1700
Data Index: 4368712 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.3434. Min Act: -0.1700
Data Index: 454816 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7811134 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.3122. Min Act: -0.1700
Data Index: 6484011 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2497. Min Act: -0.1700
Data Index: 5212742 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2184. Min Act: -0.1700
Data Index: 6612277 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2184. Min Act: -0.1700
Data Index: 4643091 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2184. Min Act: -0.1700
Data Index: 1886896 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2184. Min Act: -0.1700
Data Index: 97586 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.2184. Min Act: -0.1700
Data Index: 8151029 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.1872. Min Act: -0.1700
Data Index: 5705211 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.1559. Min Act: -0.1700
Data Index: 5967295 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.1247. Min Act: -0.1700
Data Index: 3048419 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.1247. Min Act: -0.1700
Data Index: 5755869 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.1247. Min Act: -0.1700
Data Index: 5722 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0309. Min Range: -7.0309
Max Act: 6.0934. Min Act: -0.1700
Data Index: 4628680 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19