Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.3805. Min Act: -0.1700
Data Index: 2169636 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.3180. Min Act: -0.1700
Data Index: 4942034 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.1930. Min Act: -0.1700
Data Index: 5871773 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.1305. Min Act: -0.1700
Data Index: 4311452 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.0680. Min Act: -0.1700
Data Index: 505435 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3805. Min Range: -9.3805
Max Act: 9.0055. Min Act: -0.1700
Data Index: 5610988 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6930. Min Act: -0.1700
Data Index: 7437742 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 5884773 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 3126075 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 8565650 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 1604614 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 8020114 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.6305. Min Act: -0.1700
Data Index: 5929048 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5680. Min Act: -0.1700
Data Index: 5237963 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5680. Min Act: -0.1700
Data Index: 112159 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5055. Min Act: -0.1700
Data Index: 5307620 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5055. Min Act: -0.1700
Data Index: 6239759 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5055. Min Act: -0.1700
Data Index: 1063051 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5055. Min Act: -0.1700
Data Index: 7054737 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3805. Min Range: -9.3805
Max Act: 8.5055. Min Act: -0.1700
Data Index: 2851261 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19