Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.5779. Min Act: -0.1700
Data Index: 8029963 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.4529. Min Act: -0.1700
Data Index: 7347761 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.4216. Min Act: -0.1700
Data Index: 8528759 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.4529. Min Act: -0.1700
Data Index: 235889 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3904. Min Act: -0.1700
Data Index: 6644157 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.4216. Min Act: -0.1700
Data Index: 7268061 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3904. Min Act: -0.1700
Data Index: 8029954 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3904. Min Act: -0.1700
Data Index: 6693723 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3904. Min Act: -0.1700
Data Index: 7114509 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 5636804 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 1473344 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 3672060 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 8795805 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 4134408 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 3907091 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3591. Min Act: -0.1700
Data Index: 38037 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3279. Min Act: -0.1700
Data Index: 5959533 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2679761 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2562712 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5779. Min Range: -4.5779
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2341961 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19