Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.2219. Min Act: -0.1700
Data Index: 5061605 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.1907. Min Act: -0.1700
Data Index: 6823374 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.1282. Min Act: -0.1700
Data Index: 1229952 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.0657. Min Act: -0.1700
Data Index: 6241673 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.0657. Min Act: -0.1700
Data Index: 263669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2219. Min Range: -5.2219
Max Act: 5.0032. Min Act: -0.1700
Data Index: 3469441 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9719. Min Act: -0.1700
Data Index: 4660414 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9719. Min Act: -0.1700
Data Index: 228131 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9719. Min Act: -0.1700
Data Index: 4558139 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9094. Min Act: -0.1700
Data Index: 1962421 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9094. Min Act: -0.1700
Data Index: 2645544 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.9094. Min Act: -0.1700
Data Index: 5600847 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.8782. Min Act: -0.1700
Data Index: 7576535 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.8469. Min Act: -0.1700
Data Index: 1326952 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.8469. Min Act: -0.1700
Data Index: 3772134 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.8157. Min Act: -0.1700
Data Index: 6268941 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.8157. Min Act: -0.1700
Data Index: 3793619 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.7532. Min Act: -0.1700
Data Index: 7441795 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.7844. Min Act: -0.1700
Data Index: 2896565 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2219. Min Range: -5.2219
Max Act: 4.7532. Min Act: -0.1700
Data Index: 7244845 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19