Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.1454. Min Act: -0.1700
Data Index: 1262824 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.1141. Min Act: -0.1700
Data Index: 1839617 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.1141. Min Act: -0.1700
Data Index: 713371 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.1141. Min Act: -0.1700
Data Index: 1056973 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.0829. Min Act: -0.1700
Data Index: 5913694 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.0829. Min Act: -0.1700
Data Index: 4941343 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.0204. Min Act: -0.1700
Data Index: 2360166 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2346214 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.0204. Min Act: -0.1700
Data Index: 2088663 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1454. Min Range: -6.1454
Max Act: 6.0204. Min Act: -0.1700
Data Index: 6219652 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9891. Min Act: -0.1700
Data Index: 870242 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9579. Min Act: -0.1700
Data Index: 4744543 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9891. Min Act: -0.1700
Data Index: 3442553 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9891. Min Act: -0.1700
Data Index: 622300 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9579. Min Act: -0.1700
Data Index: 4075050 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9579. Min Act: -0.1700
Data Index: 8041543 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9891. Min Act: -0.1700
Data Index: 1839618 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9579. Min Act: -0.1700
Data Index: 7540125 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9266. Min Act: -0.1700
Data Index: 1729787 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1454. Min Range: -6.1454
Max Act: 5.9266. Min Act: -0.1700
Data Index: 5764036 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19