Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4058. Min Range: -11.4058
Max Act: 11.4058. Min Act: -0.1700
Data Index: 5108484 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4058. Min Range: -11.4058
Max Act: 11.2183. Min Act: -0.1700
Data Index: 1608098 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4058. Min Range: -11.4058
Max Act: 11.0933. Min Act: -0.1700
Data Index: 5737103 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4058. Min Range: -11.4058
Max Act: 11.0308. Min Act: -0.1700
Data Index: 6562384 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.9058. Min Act: -0.1700
Data Index: 2846721 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.8433. Min Act: -0.1700
Data Index: 7435380 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.8433. Min Act: -0.1700
Data Index: 4171316 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.7808. Min Act: -0.1700
Data Index: 6979159 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.7183. Min Act: -0.1700
Data Index: 4403701 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.7183. Min Act: -0.1700
Data Index: 699600 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.6558. Min Act: -0.1700
Data Index: 1873760 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.6558. Min Act: -0.1700
Data Index: 6782236 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.6558. Min Act: -0.1700
Data Index: 7463246 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.6558. Min Act: -0.1700
Data Index: 2569598 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.5933. Min Act: -0.1700
Data Index: 2298670 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.6558. Min Act: -0.1700
Data Index: 689989 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.5933. Min Act: -0.1700
Data Index: 1081176 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.5308. Min Act: -0.1700
Data Index: 7730727 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.5308. Min Act: -0.1700
Data Index: 3028916 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4058. Min Range: -11.4058
Max Act: 10.5933. Min Act: -0.1700
Data Index: 3298114 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19