Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.6915. Min Act: -0.1700
Data Index: 5730552 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.6603. Min Act: -0.1700
Data Index: 202832 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7526975 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 6624080 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5978. Min Act: -0.1700
Data Index: 2963107 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5978. Min Act: -0.1700
Data Index: 4755322 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5978. Min Act: -0.1700
Data Index: 5537352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 4378787 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 5611940 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 1726531 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 1150003 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 5300645 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5353. Min Act: -0.1700
Data Index: 3863728 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5665. Min Act: -0.1700
Data Index: 4197105 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5353. Min Act: -0.1700
Data Index: 2812840 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5353. Min Act: -0.1700
Data Index: 5476728 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6577371 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5040. Min Act: -0.1700
Data Index: 3351071 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5040. Min Act: -0.1700
Data Index: 5388800 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6915. Min Range: -5.6915
Max Act: 5.5040. Min Act: -0.1700
Data Index: 5723133 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19