Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1494. Min Range: -5.1494
Max Act: 5.1494. Min Act: -0.1700
Data Index: 1951991 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1494. Min Range: -5.1494
Max Act: 5.0869. Min Act: -0.1700
Data Index: 4995662 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1494. Min Range: -5.1494
Max Act: 5.0557. Min Act: -0.1700
Data Index: 3629644 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9932. Min Act: -0.1700
Data Index: 4080395 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9932. Min Act: -0.1700
Data Index: 8689133 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1494. Min Range: -5.1494
Max Act: 5.0244. Min Act: -0.1700
Data Index: 8222434 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9619. Min Act: -0.1700
Data Index: 6083687 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9619. Min Act: -0.1700
Data Index: 6010961 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9619. Min Act: -0.1700
Data Index: 8020079 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9307. Min Act: -0.1700
Data Index: 7896068 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.9307. Min Act: -0.1700
Data Index: 6001955 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.8994. Min Act: -0.1700
Data Index: 3583779 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.8369. Min Act: -0.1700
Data Index: 5206122 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.8057. Min Act: -0.1700
Data Index: 2032869 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.7432. Min Act: -0.1700
Data Index: 6261533 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.7119. Min Act: -0.1700
Data Index: 167799 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.7119. Min Act: -0.1700
Data Index: 661738 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.6807. Min Act: -0.1700
Data Index: 509095 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.6807. Min Act: -0.1700
Data Index: 7498730 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1494. Min Range: -5.1494
Max Act: 4.6807. Min Act: -0.1700
Data Index: 6054811 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19