Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.6845. Min Act: -0.1700
Data Index: 3013897 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.5908. Min Act: -0.1700
Data Index: 8070164 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.4658. Min Act: -0.1700
Data Index: 5938590 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7305787 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.4033. Min Act: -0.1700
Data Index: 4996391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4397609 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3720. Min Act: -0.1700
Data Index: 7946961 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 992342 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 1120345 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 762351 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 5932450 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 2092934 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 1828985 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 5855851 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3095. Min Act: -0.1700
Data Index: 1786006 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3408. Min Act: -0.1700
Data Index: 7058558 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3095. Min Act: -0.1700
Data Index: 374933 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.3095. Min Act: -0.1700
Data Index: 1672823 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5375579 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6845. Min Range: -5.6845
Max Act: 5.2470. Min Act: -0.1700
Data Index: 1025523 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19