Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2299. Min Range: -6.2299
Max Act: 6.2299. Min Act: -0.1700
Data Index: 494388 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2299. Min Range: -6.2299
Max Act: 6.1674. Min Act: -0.1700
Data Index: 5746881 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2299. Min Range: -6.2299
Max Act: 6.0736. Min Act: -0.1700
Data Index: 2607105 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2299. Min Range: -6.2299
Max Act: 6.0111. Min Act: -0.1700
Data Index: 4173725 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.9486. Min Act: -0.1700
Data Index: 8320762 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8861. Min Act: -0.1700
Data Index: 7833746 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8861. Min Act: -0.1700
Data Index: 4162698 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8861. Min Act: -0.1700
Data Index: 7521886 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8549. Min Act: -0.1700
Data Index: 6787118 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8549. Min Act: -0.1700
Data Index: 2839997 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8549. Min Act: -0.1700
Data Index: 6064864 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8236. Min Act: -0.1700
Data Index: 8406185 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8236. Min Act: -0.1700
Data Index: 7816880 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8236. Min Act: -0.1700
Data Index: 1767890 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.8236. Min Act: -0.1700
Data Index: 2621430 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.7924. Min Act: -0.1700
Data Index: 1078920 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.7611. Min Act: -0.1700
Data Index: 2310387 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.7924. Min Act: -0.1700
Data Index: 6923209 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.7611. Min Act: -0.1700
Data Index: 8253462 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2299. Min Range: -6.2299
Max Act: 5.7611. Min Act: -0.1700
Data Index: 1194240 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19