Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.8955. Min Act: -0.1700
Data Index: 1229629 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.8330. Min Act: -0.1700
Data Index: 319569 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.7392. Min Act: -0.1700
Data Index: 3713714 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.5830. Min Act: -0.1700
Data Index: 6220678 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.5517. Min Act: -0.1700
Data Index: 7391780 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.5205. Min Act: -0.1700
Data Index: 7393005 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.4892. Min Act: -0.1700
Data Index: 4043207 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.4267. Min Act: -0.1700
Data Index: 1553580 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.4267. Min Act: -0.1700
Data Index: 4480407 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.4267. Min Act: -0.1700
Data Index: 2053128 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.4267. Min Act: -0.1700
Data Index: 8345662 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 899686 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 8737483 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 7823434 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 435143 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 4677571 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3955. Min Act: -0.1700
Data Index: 969952 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3642. Min Act: -0.1700
Data Index: 3609252 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1408117 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8955. Min Range: -4.8955
Max Act: 4.3329. Min Act: -0.1700
Data Index: 6046941 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19