Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1794. Min Range: -8.1794
Max Act: 8.1794. Min Act: -0.1700
Data Index: 4209345 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1794. Min Range: -8.1794
Max Act: 8.0544. Min Act: -0.1700
Data Index: 4823294 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1794. Min Range: -8.1794
Max Act: 8.0544. Min Act: -0.1700
Data Index: 3780500 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1794. Min Range: -8.1794
Max Act: 8.0544. Min Act: -0.1700
Data Index: 386306 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.9607. Min Act: -0.1700
Data Index: 5929568 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 8416767 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 1075063 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8357. Min Act: -0.1700
Data Index: 7260271 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8669. Min Act: -0.1700
Data Index: 7354012 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8669. Min Act: -0.1700
Data Index: 1691426 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8669. Min Act: -0.1700
Data Index: 3177909 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8044. Min Act: -0.1700
Data Index: 2801870 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8044. Min Act: -0.1700
Data Index: 2334974 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8044. Min Act: -0.1700
Data Index: 5920307 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.8357. Min Act: -0.1700
Data Index: 7988312 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.7732. Min Act: -0.1700
Data Index: 7816148 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.7732. Min Act: -0.1700
Data Index: 6081237 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.7419. Min Act: -0.1700
Data Index: 1691425 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.6794. Min Act: -0.1700
Data Index: 7861137 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1794. Min Range: -8.1794
Max Act: 7.7107. Min Act: -0.1700
Data Index: 3089750 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19