Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.9795. Min Act: -0.1700
Data Index: 4922751 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 316749 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 3663785 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 8222092 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8858. Min Act: -0.1700
Data Index: 2321647 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8233. Min Act: -0.1700
Data Index: 8181357 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.8233. Min Act: -0.1700
Data Index: 677949 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7920. Min Act: -0.1700
Data Index: 5186952 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7920. Min Act: -0.1700
Data Index: 2368765 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7920. Min Act: -0.1700
Data Index: 8440950 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7920. Min Act: -0.1700
Data Index: 3843609 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3161791 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7608. Min Act: -0.1700
Data Index: 126490 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7608. Min Act: -0.1700
Data Index: 8530515 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7608. Min Act: -0.1700
Data Index: 6244852 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7608. Min Act: -0.1700
Data Index: 220938 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7295. Min Act: -0.1700
Data Index: 8306482 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7295. Min Act: -0.1700
Data Index: 333907 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7295. Min Act: -0.1700
Data Index: 2924790 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9795. Min Range: -4.9795
Max Act: 4.7295. Min Act: -0.1700
Data Index: 5946681 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19