Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.3165. Min Act: -0.1700
Data Index: 4806440 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.2540. Min Act: -0.1700
Data Index: 5501811 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.2852. Min Act: -0.1700
Data Index: 5740841 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.2540. Min Act: -0.1700
Data Index: 2562361 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.1915. Min Act: -0.1700
Data Index: 1276748 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.1290. Min Act: -0.1700
Data Index: 1947075 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.1290. Min Act: -0.1700
Data Index: 3698105 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.1290. Min Act: -0.1700
Data Index: 3356423 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.1290. Min Act: -0.1700
Data Index: 7139196 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0977. Min Act: -0.1700
Data Index: 755121 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0977. Min Act: -0.1700
Data Index: 5159781 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0977. Min Act: -0.1700
Data Index: 6035227 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0977. Min Act: -0.1700
Data Index: 7269143 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0352. Min Act: -0.1700
Data Index: 1592132 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0665. Min Act: -0.1700
Data Index: 2051468 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0665. Min Act: -0.1700
Data Index: 4485540 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0977. Min Act: -0.1700
Data Index: 6119135 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0665. Min Act: -0.1700
Data Index: 8676132 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0352. Min Act: -0.1700
Data Index: 6472825 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3165. Min Range: -6.3165
Max Act: 6.0352. Min Act: -0.1700
Data Index: 8596980 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19