Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4357 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0994. Min Range: -6.0994
Max Act: 6.0994. Min Act: -0.1700
Data Index: 6447228 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4032318 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4600312 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.7244. Min Act: -0.1700
Data Index: 6033820 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4271446 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.7244. Min Act: -0.1700
Data Index: 6133998 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6932. Min Act: -0.1700
Data Index: 196273 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6619. Min Act: -0.1700
Data Index: 970206 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6619. Min Act: -0.1700
Data Index: 3606732 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.5994. Min Act: -0.1700
Data Index: 7854365 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4693005 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.6307. Min Act: -0.1700
Data Index: 6914154 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.5994. Min Act: -0.1700
Data Index: 3788560 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.5369. Min Act: -0.1700
Data Index: 5942842 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.5057. Min Act: -0.1700
Data Index: 868529 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.5057. Min Act: -0.1700
Data Index: 3586074 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.4744. Min Act: -0.1700
Data Index: 3641991 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.4744. Min Act: -0.1700
Data Index: 6976368 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.4432. Min Act: -0.1700
Data Index: 4283507 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0994. Min Range: -6.0994
Max Act: 5.4744. Min Act: -0.1700
Data Index: 6879709 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19