Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.3245. Min Act: -0.1700
Data Index: 6318181 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.1995. Min Act: -0.1700
Data Index: 2121568 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.1682. Min Act: -0.1700
Data Index: 5663570 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.1057. Min Act: -0.1700
Data Index: 2838150 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.0432. Min Act: -0.1700
Data Index: 2342410 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3245. Min Range: -7.3245
Max Act: 7.0120. Min Act: -0.1700
Data Index: 8477532 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.9182. Min Act: -0.1700
Data Index: 4570842 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8870. Min Act: -0.1700
Data Index: 1352749 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8557. Min Act: -0.1700
Data Index: 8608912 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.9182. Min Act: -0.1700
Data Index: 2941732 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8870. Min Act: -0.1700
Data Index: 8616572 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.9182. Min Act: -0.1700
Data Index: 8295616 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8557. Min Act: -0.1700
Data Index: 8444969 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 4071674 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 3294942 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.7620. Min Act: -0.1700
Data Index: 1401221 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 1430152 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 6528134 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.7932. Min Act: -0.1700
Data Index: 223680 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3245. Min Range: -7.3245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 4139754 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19