Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2323 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2503. Min Range: -8.2503
Max Act: 8.2503. Min Act: -0.1700
Data Index: 2907047 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2503. Min Range: -8.2503
Max Act: 8.1253. Min Act: -0.1700
Data Index: 5930476 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2503. Min Range: -8.2503
Max Act: 8.0628. Min Act: -0.1700
Data Index: 8304367 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.8753. Min Act: -0.1700
Data Index: 4697514 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.8128. Min Act: -0.1700
Data Index: 4064519 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6878. Min Act: -0.1700
Data Index: 928296 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6878. Min Act: -0.1700
Data Index: 6490827 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6878. Min Act: -0.1700
Data Index: 2180028 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6878. Min Act: -0.1700
Data Index: 715506 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6253. Min Act: -0.1700
Data Index: 7560619 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.6878. Min Act: -0.1700
Data Index: 2313317 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5940. Min Act: -0.1700
Data Index: 6798453 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5940. Min Act: -0.1700
Data Index: 5519639 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5628. Min Act: -0.1700
Data Index: 2139533 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5628. Min Act: -0.1700
Data Index: 21202 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5315. Min Act: -0.1700
Data Index: 1738978 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5315. Min Act: -0.1700
Data Index: 8635695 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5003. Min Act: -0.1700
Data Index: 8824043 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.5003. Min Act: -0.1700
Data Index: 7076036 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2503. Min Range: -8.2503
Max Act: 7.4690. Min Act: -0.1700
Data Index: 2757960 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19