Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1472. Min Range: -8.1472
Max Act: 8.1472. Min Act: -0.1700
Data Index: 6237020 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1472. Min Range: -8.1472
Max Act: 8.0222. Min Act: -0.1700
Data Index: 7585696 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.9597. Min Act: -0.1700
Data Index: 8736330 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.8972. Min Act: -0.1700
Data Index: 898740 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.8347. Min Act: -0.1700
Data Index: 1622736 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.8347. Min Act: -0.1700
Data Index: 3211664 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7722. Min Act: -0.1700
Data Index: 6277271 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7722. Min Act: -0.1700
Data Index: 8406180 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7722. Min Act: -0.1700
Data Index: 666830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7097. Min Act: -0.1700
Data Index: 6743827 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7097. Min Act: -0.1700
Data Index: 8566046 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.7097. Min Act: -0.1700
Data Index: 8617082 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.6472. Min Act: -0.1700
Data Index: 4952463 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.6472. Min Act: -0.1700
Data Index: 7144880 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5847. Min Act: -0.1700
Data Index: 8441364 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5847. Min Act: -0.1700
Data Index: 3899783 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5535. Min Act: -0.1700
Data Index: 2910119 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5222. Min Act: -0.1700
Data Index: 8107870 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3227489 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1472. Min Range: -8.1472
Max Act: 7.5222. Min Act: -0.1700
Data Index: 6974589 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19