Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.6084. Min Act: -0.1700
Data Index: 3074040 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.1084. Min Act: -0.1700
Data Index: 7257473 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.1084. Min Act: -0.1700
Data Index: 6907350 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.1084. Min Act: -0.1700
Data Index: 8388773 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.0146. Min Act: -0.1700
Data Index: 319098 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6084. Min Range: -6.6084
Max Act: 6.0146. Min Act: -0.1700
Data Index: 7924481 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.9209. Min Act: -0.1700
Data Index: 3809342 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.9209. Min Act: -0.1700
Data Index: 2144056 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.8896. Min Act: -0.1700
Data Index: 6630936 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.8896. Min Act: -0.1700
Data Index: 3531982 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1989068 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7959. Min Act: -0.1700
Data Index: 8030303 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7646. Min Act: -0.1700
Data Index: 5462677 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7334. Min Act: -0.1700
Data Index: 248708 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7646. Min Act: -0.1700
Data Index: 2934378 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7334. Min Act: -0.1700
Data Index: 2630646 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7334. Min Act: -0.1700
Data Index: 5083819 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7334. Min Act: -0.1700
Data Index: 1450195 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7021. Min Act: -0.1700
Data Index: 5677517 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6084. Min Range: -6.6084
Max Act: 5.7021. Min Act: -0.1700
Data Index: 613889 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19