Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.5948. Min Act: -0.1700
Data Index: 4823995 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.2511. Min Act: -0.1700
Data Index: 262670 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.2198. Min Act: -0.1700
Data Index: 6077747 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.1261. Min Act: -0.1700
Data Index: 1178206 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.1261. Min Act: -0.1700
Data Index: 5989403 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.1261. Min Act: -0.1700
Data Index: 3610842 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2204790 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0636. Min Act: -0.1700
Data Index: 8695641 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0636. Min Act: -0.1700
Data Index: 7495724 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6718611 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0323. Min Act: -0.1700
Data Index: 3908620 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0323. Min Act: -0.1700
Data Index: 4811357 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4935626 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0011. Min Act: -0.1700
Data Index: 2557648 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0011. Min Act: -0.1700
Data Index: 869817 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0011. Min Act: -0.1700
Data Index: 8463342 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5948. Min Range: -5.5948
Max Act: 4.9698. Min Act: -0.1700
Data Index: 464564 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5948. Min Range: -5.5948
Max Act: 5.0011. Min Act: -0.1700
Data Index: 2587651 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5948. Min Range: -5.5948
Max Act: 4.9386. Min Act: -0.1700
Data Index: 5944804 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5948. Min Range: -5.5948
Max Act: 4.9698. Min Act: -0.1700
Data Index: 6522526 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19