Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1384 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3437. Min Range: -6.3437
Max Act: 6.3437. Min Act: -0.1700
Data Index: 3887648 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3437. Min Range: -6.3437
Max Act: 6.3437. Min Act: -0.1700
Data Index: 2143564 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3437. Min Range: -6.3437
Max Act: 6.1250. Min Act: -0.1700
Data Index: 255949 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3437. Min Range: -6.3437
Max Act: 6.0312. Min Act: -0.1700
Data Index: 7799168 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3437. Min Range: -6.3437
Max Act: 6.0000. Min Act: -0.1700
Data Index: 8789926 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.9687. Min Act: -0.1700
Data Index: 6646164 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.9687. Min Act: -0.1700
Data Index: 4712350 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.9687. Min Act: -0.1700
Data Index: 8637771 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.9062. Min Act: -0.1700
Data Index: 5474733 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8750. Min Act: -0.1700
Data Index: 6387726 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8750. Min Act: -0.1700
Data Index: 7925862 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8750. Min Act: -0.1700
Data Index: 2384383 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8750. Min Act: -0.1700
Data Index: 3587225 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8437. Min Act: -0.1700
Data Index: 7614155 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8437. Min Act: -0.1700
Data Index: 7942878 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8437. Min Act: -0.1700
Data Index: 4943430 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8125. Min Act: -0.1700
Data Index: 1519893 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8125. Min Act: -0.1700
Data Index: 5805816 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.8125. Min Act: -0.1700
Data Index: 5303669 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3437. Min Range: -6.3437
Max Act: 5.7812. Min Act: -0.1700
Data Index: 7541505 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19