Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6371 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0580. Min Range: -8.0580
Max Act: 8.0580. Min Act: -0.1700
Data Index: 6828579 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.9955. Min Act: -0.1700
Data Index: 560231 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.9330. Min Act: -0.1700
Data Index: 7842758 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.8705. Min Act: -0.1700
Data Index: 5801281 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.9330. Min Act: -0.1700
Data Index: 6777378 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.6830. Min Act: -0.1700
Data Index: 8488751 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.6830. Min Act: -0.1700
Data Index: 2866339 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.5580. Min Act: -0.1700
Data Index: 6816894 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.5580. Min Act: -0.1700
Data Index: 295142 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.5580. Min Act: -0.1700
Data Index: 7070960 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.4955. Min Act: -0.1700
Data Index: 3165998 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.4955. Min Act: -0.1700
Data Index: 3524032 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.4955. Min Act: -0.1700
Data Index: 2900678 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.4642. Min Act: -0.1700
Data Index: 3328723 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.4330. Min Act: -0.1700
Data Index: 5755597 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.3705. Min Act: -0.1700
Data Index: 3266400 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.3705. Min Act: -0.1700
Data Index: 6483027 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.3705. Min Act: -0.1700
Data Index: 4770717 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.3705. Min Act: -0.1700
Data Index: 1979753 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0580. Min Range: -8.0580
Max Act: 7.3392. Min Act: -0.1700
Data Index: 2014347 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19