Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2288 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.5580. Min Act: -0.1700
Data Index: 5148558 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.3705. Min Act: -0.1700
Data Index: 5808383 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 6469806 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1517. Min Act: -0.1700
Data Index: 1490523 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3690126 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.0267. Min Act: -0.1700
Data Index: 2699190 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9955. Min Act: -0.1700
Data Index: 2237260 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9642. Min Act: -0.1700
Data Index: 6151051 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9642. Min Act: -0.1700
Data Index: 1327045 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9330. Min Act: -0.1700
Data Index: 4426021 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9642. Min Act: -0.1700
Data Index: 7051558 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9330. Min Act: -0.1700
Data Index: 2733002 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9017. Min Act: -0.1700
Data Index: 3892036 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9330. Min Act: -0.1700
Data Index: 5217097 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.8705. Min Act: -0.1700
Data Index: 1656213 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9330. Min Act: -0.1700
Data Index: 3537306 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.9017. Min Act: -0.1700
Data Index: 6921875 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.8705. Min Act: -0.1700
Data Index: 3307891 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.8392. Min Act: -0.1700
Data Index: 7049461 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5580. Min Range: -6.5580
Max Act: 5.8392. Min Act: -0.1700
Data Index: 6134696 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19