Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.2915. Min Act: -0.1700
Data Index: 5750554 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.2290. Min Act: -0.1700
Data Index: 6217769 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.1665. Min Act: -0.1700
Data Index: 3876423 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.1040. Min Act: -0.1700
Data Index: 1003793 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.0415. Min Act: -0.1700
Data Index: 890676 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2915. Min Range: -8.2915
Max Act: 8.0415. Min Act: -0.1700
Data Index: 3399808 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.9790. Min Act: -0.1700
Data Index: 3825916 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.9165. Min Act: -0.1700
Data Index: 4312720 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.9790. Min Act: -0.1700
Data Index: 239129 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.9165. Min Act: -0.1700
Data Index: 3790089 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.8540. Min Act: -0.1700
Data Index: 8590105 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.8540. Min Act: -0.1700
Data Index: 4960442 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 3996609 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 6096091 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 6120533 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 6670009 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 999780 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7290. Min Act: -0.1700
Data Index: 1681460 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7915. Min Act: -0.1700
Data Index: 7571169 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2915. Min Range: -8.2915
Max Act: 7.7290. Min Act: -0.1700
Data Index: 4463085 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19