Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.6905. Min Act: -0.1700
Data Index: 5869058 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.3468. Min Act: -0.1700
Data Index: 3250330 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.3780. Min Act: -0.1700
Data Index: 6208602 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.2843. Min Act: -0.1700
Data Index: 734305 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.2218. Min Act: -0.1700
Data Index: 2476545 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.1905. Min Act: -0.1700
Data Index: 5992083 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.1593. Min Act: -0.1700
Data Index: 1382837 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.1593. Min Act: -0.1700
Data Index: 3557038 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.1280. Min Act: -0.1700
Data Index: 8250436 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.1280. Min Act: -0.1700
Data Index: 6613684 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0968. Min Act: -0.1700
Data Index: 4494794 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0968. Min Act: -0.1700
Data Index: 3906315 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0343. Min Act: -0.1700
Data Index: 2952646 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0655. Min Act: -0.1700
Data Index: 3804697 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0343. Min Act: -0.1700
Data Index: 6520134 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0343. Min Act: -0.1700
Data Index: 7978268 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0030. Min Act: -0.1700
Data Index: 8084930 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6905. Min Range: -6.6905
Max Act: 5.9718. Min Act: -0.1700
Data Index: 6734308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6905. Min Range: -6.6905
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1808529 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6905. Min Range: -6.6905
Max Act: 6.0030. Min Act: -0.1700
Data Index: 5616466 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19