Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.9887. Min Act: -0.1700
Data Index: 1891330 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.9262. Min Act: -0.1700
Data Index: 1725711 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.8950. Min Act: -0.1700
Data Index: 5431961 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.8324. Min Act: -0.1700
Data Index: 1068010 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.8324. Min Act: -0.1700
Data Index: 3777349 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.8168. Min Act: -0.1700
Data Index: 2819111 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.8324. Min Act: -0.1700
Data Index: 7636732 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7699. Min Act: -0.1700
Data Index: 6824811 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7542. Min Act: -0.1700
Data Index: 3597648 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7699. Min Act: -0.1700
Data Index: 6241412 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7386. Min Act: -0.1700
Data Index: 438682 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7073. Min Act: -0.1700
Data Index: 8312809 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7230. Min Act: -0.1700
Data Index: 3715594 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7230. Min Act: -0.1700
Data Index: 6299760 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7230. Min Act: -0.1700
Data Index: 6029103 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.7230. Min Act: -0.1700
Data Index: 7513396 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.6917. Min Act: -0.1700
Data Index: 4117800 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.6760. Min Act: -0.1700
Data Index: 4901001 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.6917. Min Act: -0.1700
Data Index: 2187949 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9887. Min Range: -3.9887
Max Act: 3.6760. Min Act: -0.1700
Data Index: 6067620 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19