Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.3651. Min Act: -0.1700
Data Index: 1655700 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.3026. Min Act: -0.1700
Data Index: 2327776 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.1776. Min Act: -0.1700
Data Index: 5850667 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.1776. Min Act: -0.1700
Data Index: 644872 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.1776. Min Act: -0.1700
Data Index: 6280795 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.1151. Min Act: -0.1700
Data Index: 2260319 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3651. Min Range: -8.3651
Max Act: 8.1151. Min Act: -0.1700
Data Index: 5736364 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.9276. Min Act: -0.1700
Data Index: 8801911 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8964. Min Act: -0.1700
Data Index: 4746267 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8964. Min Act: -0.1700
Data Index: 8374031 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8651. Min Act: -0.1700
Data Index: 4945133 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8339. Min Act: -0.1700
Data Index: 1983765 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8026. Min Act: -0.1700
Data Index: 3535759 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8339. Min Act: -0.1700
Data Index: 6023056 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8651. Min Act: -0.1700
Data Index: 7657721 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.7714. Min Act: -0.1700
Data Index: 5785666 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8026. Min Act: -0.1700
Data Index: 1606258 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8026. Min Act: -0.1700
Data Index: 2171908 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.8026. Min Act: -0.1700
Data Index: 8331753 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3651. Min Range: -8.3651
Max Act: 7.7714. Min Act: -0.1700
Data Index: 5424040 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19