Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2673. Min Range: -7.2673
Max Act: 7.2673. Min Act: -0.1700
Data Index: 6158137 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.7048. Min Act: -0.1700
Data Index: 4102606 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.5173. Min Act: -0.1700
Data Index: 595415 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.5486. Min Act: -0.1700
Data Index: 420813 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.5173. Min Act: -0.1700
Data Index: 3139535 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4861. Min Act: -0.1700
Data Index: 54240 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4236. Min Act: -0.1700
Data Index: 7559118 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4861. Min Act: -0.1700
Data Index: 3164206 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4236. Min Act: -0.1700
Data Index: 8714166 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4236. Min Act: -0.1700
Data Index: 4812367 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4236. Min Act: -0.1700
Data Index: 7525402 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.4236. Min Act: -0.1700
Data Index: 7823229 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.3923. Min Act: -0.1700
Data Index: 2858655 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.3611. Min Act: -0.1700
Data Index: 837879 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.3298. Min Act: -0.1700
Data Index: 8417540 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7852386 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.2673. Min Act: -0.1700
Data Index: 4167725 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.2986. Min Act: -0.1700
Data Index: 740260 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.2673. Min Act: -0.1700
Data Index: 5542624 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2673. Min Range: -7.2673
Max Act: 6.2673. Min Act: -0.1700
Data Index: 2832549 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19