Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0473. Min Range: -5.0473
Max Act: 5.0473. Min Act: -0.1700
Data Index: 5213390 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0473. Min Range: -5.0473
Max Act: 5.0473. Min Act: -0.1700
Data Index: 3421853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9848. Min Act: -0.1700
Data Index: 2435469 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9848. Min Act: -0.1700
Data Index: 2435463 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9848. Min Act: -0.1700
Data Index: 2873641 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9848. Min Act: -0.1700
Data Index: 2513304 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9536. Min Act: -0.1700
Data Index: 4390147 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9536. Min Act: -0.1700
Data Index: 2435449 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9536. Min Act: -0.1700
Data Index: 2435462 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.8911. Min Act: -0.1700
Data Index: 2854486 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 262985 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2435460 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2435467 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 287195 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 7258261 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9536. Min Act: -0.1700
Data Index: 2435461 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2435473 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.8911. Min Act: -0.1700
Data Index: 1104191 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.8911. Min Act: -0.1700
Data Index: 41600 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0473. Min Range: -5.0473
Max Act: 4.8911. Min Act: -0.1700
Data Index: 2435465 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19