Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.8812. Min Act: -0.1700
Data Index: 8527955 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.7562. Min Act: -0.1700
Data Index: 6166803 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.7562. Min Act: -0.1700
Data Index: 1564615 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.7562. Min Act: -0.1700
Data Index: 2360551 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.6937. Min Act: -0.1700
Data Index: 1815309 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.6312. Min Act: -0.1700
Data Index: 8427957 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.6312. Min Act: -0.1700
Data Index: 876823 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.6312. Min Act: -0.1700
Data Index: 876193 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.5375. Min Act: -0.1700
Data Index: 5930538 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.5687. Min Act: -0.1700
Data Index: 8268344 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.5062. Min Act: -0.1700
Data Index: 5982658 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4750. Min Act: -0.1700
Data Index: 2800008 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4750. Min Act: -0.1700
Data Index: 4146302 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4437. Min Act: -0.1700
Data Index: 7843452 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4125. Min Act: -0.1700
Data Index: 6120453 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4437. Min Act: -0.1700
Data Index: 5748587 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4437. Min Act: -0.1700
Data Index: 6367589 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.3812. Min Act: -0.1700
Data Index: 7064263 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.4125. Min Act: -0.1700
Data Index: 907811 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8812. Min Range: -7.8812
Max Act: 7.3812. Min Act: -0.1700
Data Index: 2388664 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19