Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.4309. Min Act: -0.1700
Data Index: 348484 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.3684. Min Act: -0.1700
Data Index: 8601796 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.3684. Min Act: -0.1700
Data Index: 1708060 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.3372. Min Act: -0.1700
Data Index: 1527325 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.3059. Min Act: -0.1700
Data Index: 3927663 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.3059. Min Act: -0.1700
Data Index: 1468947 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2434. Min Act: -0.1700
Data Index: 3263977 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2284331 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2434. Min Act: -0.1700
Data Index: 345308 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2434. Min Act: -0.1700
Data Index: 1849523 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2882305 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2122. Min Act: -0.1700
Data Index: 2690395 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.1809. Min Act: -0.1700
Data Index: 2055340 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2122. Min Act: -0.1700
Data Index: 7067399 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4579912 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.2122. Min Act: -0.1700
Data Index: 7102058 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.1809. Min Act: -0.1700
Data Index: 3212079 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.1809. Min Act: -0.1700
Data Index: 8547699 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.1809. Min Act: -0.1700
Data Index: 6929657 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4309. Min Range: -5.4309
Max Act: 5.1497. Min Act: -0.1700
Data Index: 5367201 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19