Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5222. Min Range: -6.5222
Max Act: 6.5222. Min Act: -0.1700
Data Index: 6405905 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5222. Min Range: -6.5222
Max Act: 6.4284. Min Act: -0.1700
Data Index: 7796669 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5222. Min Range: -6.5222
Max Act: 6.0847. Min Act: -0.1700
Data Index: 8744089 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.9284. Min Act: -0.1700
Data Index: 8355451 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.9284. Min Act: -0.1700
Data Index: 6128908 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8659. Min Act: -0.1700
Data Index: 4366389 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8972. Min Act: -0.1700
Data Index: 8079267 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8347. Min Act: -0.1700
Data Index: 58911 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8347. Min Act: -0.1700
Data Index: 1598407 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7720789 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.8034. Min Act: -0.1700
Data Index: 4069347 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.7409. Min Act: -0.1700
Data Index: 2360279 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.7722. Min Act: -0.1700
Data Index: 2150146 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.7409. Min Act: -0.1700
Data Index: 2835038 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.6784. Min Act: -0.1700
Data Index: 8039377 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.7097. Min Act: -0.1700
Data Index: 3741140 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.6784. Min Act: -0.1700
Data Index: 1155473 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.6784. Min Act: -0.1700
Data Index: 4762724 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.6784. Min Act: -0.1700
Data Index: 4861260 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5222. Min Range: -6.5222
Max Act: 5.6784. Min Act: -0.1700
Data Index: 2525125 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19