Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.9017. Min Act: -0.1700
Data Index: 1144078 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.9017. Min Act: -0.1700
Data Index: 4132792 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.8080. Min Act: -0.1700
Data Index: 2899279 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 79046 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 3541090 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 536679 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 3273926 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 8335376 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 4401566 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 951801 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.6517. Min Act: -0.1700
Data Index: 8458073 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5892. Min Act: -0.1700
Data Index: 7456321 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5892. Min Act: -0.1700
Data Index: 8719129 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5267. Min Act: -0.1700
Data Index: 3003588 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 2000725 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 8584697 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 322238 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 4289332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5580. Min Act: -0.1700
Data Index: 2262077 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9017. Min Range: -4.9017
Max Act: 4.5267. Min Act: -0.1700
Data Index: 5181834 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19