Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1779 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0467. Min Range: -6.0467
Max Act: 6.0154. Min Act: -0.1700
Data Index: 2447216 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0467. Min Range: -6.0467
Max Act: 6.0467. Min Act: -0.1700
Data Index: 7790973 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0467. Min Range: -6.0467
Max Act: 6.0154. Min Act: -0.1700
Data Index: 1161838 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.8904. Min Act: -0.1700
Data Index: 3436585 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.9217. Min Act: -0.1700
Data Index: 1220344 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.8279. Min Act: -0.1700
Data Index: 8798639 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.8592. Min Act: -0.1700
Data Index: 3930846 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.7654. Min Act: -0.1700
Data Index: 1879200 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.7967. Min Act: -0.1700
Data Index: 7365814 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.7342. Min Act: -0.1700
Data Index: 5255475 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6717. Min Act: -0.1700
Data Index: 8060186 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6717. Min Act: -0.1700
Data Index: 6958167 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6717. Min Act: -0.1700
Data Index: 5326412 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6717. Min Act: -0.1700
Data Index: 1023789 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.7029. Min Act: -0.1700
Data Index: 1419996 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6404. Min Act: -0.1700
Data Index: 350222 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.6404. Min Act: -0.1700
Data Index: 4698164 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.5779. Min Act: -0.1700
Data Index: 7983116 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.5779. Min Act: -0.1700
Data Index: 4652170 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0467. Min Range: -6.0467
Max Act: 5.5779. Min Act: -0.1700
Data Index: 5393425 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19