Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0685. Min Range: -8.0685
Max Act: 8.0685. Min Act: -0.1700
Data Index: 836111 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8810. Min Act: -0.1700
Data Index: 8338620 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8810. Min Act: -0.1700
Data Index: 2064498 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8185. Min Act: -0.1700
Data Index: 3114954 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8185. Min Act: -0.1700
Data Index: 7660720 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8185. Min Act: -0.1700
Data Index: 2816229 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8185. Min Act: -0.1700
Data Index: 4657862 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 3421425 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 3009537 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 8388529 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 5996711 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 2064496 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.7560. Min Act: -0.1700
Data Index: 4626864 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.8185. Min Act: -0.1700
Data Index: 7153887 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6935. Min Act: -0.1700
Data Index: 8348854 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6935. Min Act: -0.1700
Data Index: 8160647 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6935. Min Act: -0.1700
Data Index: 1436123 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6935. Min Act: -0.1700
Data Index: 6935972 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6310. Min Act: -0.1700
Data Index: 6180153 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0685. Min Range: -8.0685
Max Act: 7.6310. Min Act: -0.1700
Data Index: 6820575 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19