Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.5915. Min Act: -0.1700
Data Index: 10960 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.3728. Min Act: -0.1700
Data Index: 1065196 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.4040. Min Act: -0.1700
Data Index: 8064490 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.3103. Min Act: -0.1700
Data Index: 7930392 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.2478. Min Act: -0.1700
Data Index: 8130018 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.2165. Min Act: -0.1700
Data Index: 1790785 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.2165. Min Act: -0.1700
Data Index: 6810266 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.2165. Min Act: -0.1700
Data Index: 5964461 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.2165. Min Act: -0.1700
Data Index: 7764089 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.1853. Min Act: -0.1700
Data Index: 3819102 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.1540. Min Act: -0.1700
Data Index: 4800621 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.1228. Min Act: -0.1700
Data Index: 725412 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 8356027 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.1228. Min Act: -0.1700
Data Index: 155472 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 1473852 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 8456001 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3105056 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 526326 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.1228. Min Act: -0.1700
Data Index: 3204402 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5915. Min Range: -5.5915
Max Act: 5.0603. Min Act: -0.1700
Data Index: 1305376 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19