Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.6256. Min Act: -0.1700
Data Index: 8625530 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.4694. Min Act: -0.1700
Data Index: 4770146 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.5006. Min Act: -0.1700
Data Index: 7885620 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.4381. Min Act: -0.1700
Data Index: 3576467 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.3444. Min Act: -0.1700
Data Index: 5332521 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.2819. Min Act: -0.1700
Data Index: 8375630 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.2506. Min Act: -0.1700
Data Index: 3968022 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.2506. Min Act: -0.1700
Data Index: 6581641 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5052909 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1569. Min Act: -0.1700
Data Index: 8571768 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1881. Min Act: -0.1700
Data Index: 1193230 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1881. Min Act: -0.1700
Data Index: 6659975 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1256. Min Act: -0.1700
Data Index: 4967706 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1256. Min Act: -0.1700
Data Index: 971764 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.1256. Min Act: -0.1700
Data Index: 2193512 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.0631. Min Act: -0.1700
Data Index: 7662593 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.0631. Min Act: -0.1700
Data Index: 1564681 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.0944. Min Act: -0.1700
Data Index: 5688034 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.0631. Min Act: -0.1700
Data Index: 6620901 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6256. Min Range: -6.6256
Max Act: 6.0944. Min Act: -0.1700
Data Index: 2916667 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19