Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.8225. Min Act: -0.1700
Data Index: 1627086 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.7600. Min Act: -0.1700
Data Index: 1041299 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.6350. Min Act: -0.1700
Data Index: 512397 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.5412. Min Act: -0.1700
Data Index: 2923723 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.5100. Min Act: -0.1700
Data Index: 94041 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.4162. Min Act: -0.1700
Data Index: 8309991 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.4162. Min Act: -0.1700
Data Index: 838840 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.4162. Min Act: -0.1700
Data Index: 1852655 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.3850. Min Act: -0.1700
Data Index: 4230942 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.3537. Min Act: -0.1700
Data Index: 3729353 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.3537. Min Act: -0.1700
Data Index: 7417991 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.2600. Min Act: -0.1700
Data Index: 2988590 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.2912. Min Act: -0.1700
Data Index: 4591653 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.2600. Min Act: -0.1700
Data Index: 838839 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.2287. Min Act: -0.1700
Data Index: 4576368 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.1975. Min Act: -0.1700
Data Index: 4306685 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.1975. Min Act: -0.1700
Data Index: 7218561 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.1975. Min Act: -0.1700
Data Index: 715788 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.1975. Min Act: -0.1700
Data Index: 5235749 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8225. Min Range: -7.8225
Max Act: 7.1975. Min Act: -0.1700
Data Index: 4288548 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19