Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2439 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.7724. Min Act: -0.1700
Data Index: 1568572 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.6474. Min Act: -0.1700
Data Index: 5763948 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.6474. Min Act: -0.1700
Data Index: 6510712 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5849. Min Act: -0.1700
Data Index: 998783 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5849. Min Act: -0.1700
Data Index: 1482784 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5849. Min Act: -0.1700
Data Index: 8395730 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5849. Min Act: -0.1700
Data Index: 1855375 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5849. Min Act: -0.1700
Data Index: 1967791 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 7600988 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 5526061 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 5173651 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 6534548 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 4692264 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 2073955 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.5224. Min Act: -0.1700
Data Index: 1265372 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.4599. Min Act: -0.1700
Data Index: 7373467 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.3974. Min Act: -0.1700
Data Index: 2190445 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.4599. Min Act: -0.1700
Data Index: 7483445 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.3974. Min Act: -0.1700
Data Index: 4500370 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7724. Min Range: -10.7724
Max Act: 10.3974. Min Act: -0.1700
Data Index: 2544018 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19