Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 624 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 7946071 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5556739 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2397. Min Act: -0.1700
Data Index: 7221550 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6589023 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.1147. Min Act: -0.1700
Data Index: 2160615 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0834. Min Act: -0.1700
Data Index: 8467657 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0834. Min Act: -0.1700
Data Index: 8516931 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0522. Min Act: -0.1700
Data Index: 5377780 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0834. Min Act: -0.1700
Data Index: 2738202 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0522. Min Act: -0.1700
Data Index: 4326367 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0522. Min Act: -0.1700
Data Index: 3424166 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0522. Min Act: -0.1700
Data Index: 7666709 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6026399 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 5691991 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 6643725 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 7531397 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9897. Min Act: -0.1700
Data Index: 1794904 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 2783892 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 4875264 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9272. Min Act: -0.1700
Data Index: 4423090 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19