Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1392 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0036. Min Range: -12.0036
Max Act: 12.0036. Min Act: -0.1700
Data Index: 3709804 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.8161. Min Act: -0.1700
Data Index: 7970011 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.3786. Min Act: -0.1700
Data Index: 210622 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.3161. Min Act: -0.1700
Data Index: 3950687 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.3161. Min Act: -0.1700
Data Index: 2681651 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.2536. Min Act: -0.1700
Data Index: 773166 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.2536. Min Act: -0.1700
Data Index: 7524874 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.2536. Min Act: -0.1700
Data Index: 599871 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.1911. Min Act: -0.1700
Data Index: 2688895 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.1286. Min Act: -0.1700
Data Index: 5584606 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.1286. Min Act: -0.1700
Data Index: 5843881 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.1286. Min Act: -0.1700
Data Index: 340909 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.1286. Min Act: -0.1700
Data Index: 8727625 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.0661. Min Act: -0.1700
Data Index: 1208792 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.0661. Min Act: -0.1700
Data Index: 1597631 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.0661. Min Act: -0.1700
Data Index: 4452010 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.0036. Min Act: -0.1700
Data Index: 3469104 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0036. Min Range: -12.0036
Max Act: 11.0036. Min Act: -0.1700
Data Index: 7047906 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0036. Min Range: -12.0036
Max Act: 10.9411. Min Act: -0.1700
Data Index: 3332961 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0036. Min Range: -12.0036
Max Act: 10.9411. Min Act: -0.1700
Data Index: 5380015 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19