Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1451. Min Range: -5.1451
Max Act: 5.1451. Min Act: -0.1700
Data Index: 4860094 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1451. Min Range: -5.1451
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3589328 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.9889. Min Act: -0.1700
Data Index: 2632000 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.9264. Min Act: -0.1700
Data Index: 288601 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.9576. Min Act: -0.1700
Data Index: 3884934 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.9264. Min Act: -0.1700
Data Index: 249503 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1438427 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1727730 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1493295 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8639. Min Act: -0.1700
Data Index: 786802 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8326. Min Act: -0.1700
Data Index: 321331 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8326. Min Act: -0.1700
Data Index: 547106 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8014. Min Act: -0.1700
Data Index: 997880 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8014. Min Act: -0.1700
Data Index: 1226092 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.8014. Min Act: -0.1700
Data Index: 361256 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.7701. Min Act: -0.1700
Data Index: 5221645 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.7701. Min Act: -0.1700
Data Index: 2125151 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.7701. Min Act: -0.1700
Data Index: 3612939 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.7389. Min Act: -0.1700
Data Index: 3216722 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1451. Min Range: -5.1451
Max Act: 4.7389. Min Act: -0.1700
Data Index: 3353448 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19