Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.3482. Min Act: -0.1700
Data Index: 7348110 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0670. Min Act: -0.1700
Data Index: 5268133 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0670. Min Act: -0.1700
Data Index: 2890135 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0357. Min Act: -0.1700
Data Index: 6679446 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0357. Min Act: -0.1700
Data Index: 5013996 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0045. Min Act: -0.1700
Data Index: 33899 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3482. Min Range: -6.3482
Max Act: 6.0045. Min Act: -0.1700
Data Index: 4687614 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9732. Min Act: -0.1700
Data Index: 7001674 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9420. Min Act: -0.1700
Data Index: 745017 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9420. Min Act: -0.1700
Data Index: 1688613 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4040409 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9107. Min Act: -0.1700
Data Index: 1815650 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8795. Min Act: -0.1700
Data Index: 1185610 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8795. Min Act: -0.1700
Data Index: 3785622 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8795. Min Act: -0.1700
Data Index: 847559 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.9107. Min Act: -0.1700
Data Index: 8331738 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8795. Min Act: -0.1700
Data Index: 3454907 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8482. Min Act: -0.1700
Data Index: 3625548 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8482. Min Act: -0.1700
Data Index: 3553139 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3482. Min Range: -6.3482
Max Act: 5.8482. Min Act: -0.1700
Data Index: 1893417 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19