Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2519 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.8866. Min Act: -0.1700
Data Index: 2031487 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.7303. Min Act: -0.1700
Data Index: 1283250 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.6366. Min Act: -0.1700
Data Index: 8672095 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.5741. Min Act: -0.1700
Data Index: 6199919 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.5741. Min Act: -0.1700
Data Index: 1747278 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.5741. Min Act: -0.1700
Data Index: 8728027 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.5116. Min Act: -0.1700
Data Index: 8422193 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.4491. Min Act: -0.1700
Data Index: 2742318 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.4178. Min Act: -0.1700
Data Index: 575330 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.3241. Min Act: -0.1700
Data Index: 828358 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.3241. Min Act: -0.1700
Data Index: 5769873 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.3241. Min Act: -0.1700
Data Index: 3649937 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.2928. Min Act: -0.1700
Data Index: 6891224 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.2928. Min Act: -0.1700
Data Index: 3661592 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.2928. Min Act: -0.1700
Data Index: 6531857 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.2303. Min Act: -0.1700
Data Index: 266554 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.2303. Min Act: -0.1700
Data Index: 6542413 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.1678. Min Act: -0.1700
Data Index: 1739113 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.1678. Min Act: -0.1700
Data Index: 4869388 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8866. Min Range: -7.8866
Max Act: 7.1991. Min Act: -0.1700
Data Index: 8267257 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19