Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2802. Min Range: -7.2802
Max Act: 7.2802. Min Act: -0.1700
Data Index: 5645324 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9365. Min Act: -0.1700
Data Index: 1860332 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.9052. Min Act: -0.1700
Data Index: 8107850 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8427. Min Act: -0.1700
Data Index: 6837175 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.8115. Min Act: -0.1700
Data Index: 523607 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7177. Min Act: -0.1700
Data Index: 1578455 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.7177. Min Act: -0.1700
Data Index: 2301156 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6865. Min Act: -0.1700
Data Index: 1273966 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6865. Min Act: -0.1700
Data Index: 7518908 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6865. Min Act: -0.1700
Data Index: 8107852 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6552. Min Act: -0.1700
Data Index: 6276805 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6122630 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.6240. Min Act: -0.1700
Data Index: 3223565 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5615. Min Act: -0.1700
Data Index: 6310590 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5927. Min Act: -0.1700
Data Index: 5456616 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5615. Min Act: -0.1700
Data Index: 3659728 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5615. Min Act: -0.1700
Data Index: 1906018 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5615. Min Act: -0.1700
Data Index: 2997737 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.5302. Min Act: -0.1700
Data Index: 4607133 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2802. Min Range: -7.2802
Max Act: 6.4990. Min Act: -0.1700
Data Index: 829535 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19