Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.4740. Min Act: -0.1700
Data Index: 7330905 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.3015. Min Act: -0.1700
Data Index: 8568290 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.2701. Min Act: -0.1700
Data Index: 5740832 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1915. Min Act: -0.1700
Data Index: 6118697 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.2072. Min Act: -0.1700
Data Index: 5996688 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1757. Min Act: -0.1700
Data Index: 8098215 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1285. Min Act: -0.1700
Data Index: 4019769 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1285. Min Act: -0.1700
Data Index: 4507222 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1128. Min Act: -0.1700
Data Index: 7364541 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.1285. Min Act: -0.1700
Data Index: 151886 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0655. Min Act: -0.1700
Data Index: 8274546 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0655. Min Act: -0.1700
Data Index: 6546407 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0812. Min Act: -0.1700
Data Index: 4492081 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0812. Min Act: -0.1700
Data Index: 229413 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0655. Min Act: -0.1700
Data Index: 4651040 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0655. Min Act: -0.1700
Data Index: 4582622 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0497. Min Act: -0.1700
Data Index: 874004 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0655. Min Act: -0.1700
Data Index: 3488974 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0497. Min Act: -0.1700
Data Index: 8180117 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4740. Min Range: -3.4740
Max Act: 3.0339. Min Act: -0.1700
Data Index: 3208129 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19