Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.7954. Min Act: -0.1700
Data Index: 4425888 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.2954. Min Act: -0.1700
Data Index: 967207 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.1704. Min Act: -0.1700
Data Index: 6748995 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.1391. Min Act: -0.1700
Data Index: 8054064 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.1704. Min Act: -0.1700
Data Index: 3787841 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.0141. Min Act: -0.1700
Data Index: 5650581 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7954. Min Range: -5.7954
Max Act: 5.0141. Min Act: -0.1700
Data Index: 2864421 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 6312585 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 6461183 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 3758732 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 8215318 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 5291526 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 1806506 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 8697671 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9204. Min Act: -0.1700
Data Index: 8495616 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.8891. Min Act: -0.1700
Data Index: 4668378 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.8891. Min Act: -0.1700
Data Index: 6472830 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.9204. Min Act: -0.1700
Data Index: 1857290 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.8891. Min Act: -0.1700
Data Index: 7262771 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7954. Min Range: -5.7954
Max Act: 4.8579. Min Act: -0.1700
Data Index: 152561 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19