Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.0308. Min Range: -5.0308
Max Act: 5.0308. Min Act: -0.1700
Data Index: 2843973 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.8433. Min Act: -0.1700
Data Index: 146709 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.8433. Min Act: -0.1700
Data Index: 4459865 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 5405799 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 4059358 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 4848772 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 2704445 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6670359 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 925172 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6245. Min Act: -0.1700
Data Index: 1411658 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6245. Min Act: -0.1700
Data Index: 2062738 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 6885358 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 3029740 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5620. Min Act: -0.1700
Data Index: 8089890 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 7308771 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 3208737 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 1859483 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 6254597 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5620. Min Act: -0.1700
Data Index: 8401188 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5620. Min Act: -0.1700
Data Index: 58146 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19