Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1837. Min Act: -0.1700
Data Index: 1881638 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1522. Min Act: -0.1700
Data Index: 5185293 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1050. Min Act: -0.1700
Data Index: 8298497 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0892. Min Act: -0.1700
Data Index: 1667839 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0261. Min Act: -0.1700
Data Index: 8751797 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 2498718 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 7843281 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 1836783 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 809504 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 163967 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 7163222 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9945. Min Act: -0.1700
Data Index: 4821454 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9945. Min Act: -0.1700
Data Index: 3267993 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9945. Min Act: -0.1700
Data Index: 8410396 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9629. Min Act: -0.1700
Data Index: 870327 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9629. Min Act: -0.1700
Data Index: 2494560 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9471. Min Act: -0.1700
Data Index: 6294176 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9629. Min Act: -0.1700
Data Index: 4829328 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9629. Min Act: -0.1700
Data Index: 90038 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9471. Min Act: -0.1700
Data Index: 5599851 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19