Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 343 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1382. Min Range: -8.1382
Max Act: 8.1382. Min Act: -0.1700
Data Index: 1052851 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1382. Min Range: -8.1382
Max Act: 8.0757. Min Act: -0.1700
Data Index: 5495365 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1382. Min Range: -8.1382
Max Act: 8.0757. Min Act: -0.1700
Data Index: 1198729 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1382. Min Range: -8.1382
Max Act: 8.0132. Min Act: -0.1700
Data Index: 5053974 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.8257. Min Act: -0.1700
Data Index: 5265591 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.7632. Min Act: -0.1700
Data Index: 2053723 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.7320. Min Act: -0.1700
Data Index: 6663180 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.6070. Min Act: -0.1700
Data Index: 4671195 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.6070. Min Act: -0.1700
Data Index: 4737762 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.5132. Min Act: -0.1700
Data Index: 4545749 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.5132. Min Act: -0.1700
Data Index: 3970465 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.5132. Min Act: -0.1700
Data Index: 8648325 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.5445. Min Act: -0.1700
Data Index: 7205096 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4820. Min Act: -0.1700
Data Index: 5501137 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4820. Min Act: -0.1700
Data Index: 1048900 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4820. Min Act: -0.1700
Data Index: 6515156 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.5132. Min Act: -0.1700
Data Index: 5639356 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4507. Min Act: -0.1700
Data Index: 7130551 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4195. Min Act: -0.1700
Data Index: 5885463 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1382. Min Range: -8.1382
Max Act: 7.4195. Min Act: -0.1700
Data Index: 7159544 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19