Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3247. Min Range: -6.3247
Max Act: 6.3247. Min Act: -0.1700
Data Index: 6972166 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3247. Min Range: -6.3247
Max Act: 6.1685. Min Act: -0.1700
Data Index: 520931 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3247. Min Range: -6.3247
Max Act: 6.0122. Min Act: -0.1700
Data Index: 3781839 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.9810. Min Act: -0.1700
Data Index: 8513126 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.9497. Min Act: -0.1700
Data Index: 2917542 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8560. Min Act: -0.1700
Data Index: 8811423 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8560. Min Act: -0.1700
Data Index: 8207667 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8560. Min Act: -0.1700
Data Index: 2388221 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8560. Min Act: -0.1700
Data Index: 5196059 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8872. Min Act: -0.1700
Data Index: 1088555 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8247. Min Act: -0.1700
Data Index: 3701075 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7935. Min Act: -0.1700
Data Index: 794645 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7935. Min Act: -0.1700
Data Index: 2480135 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7935. Min Act: -0.1700
Data Index: 1606741 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.8247. Min Act: -0.1700
Data Index: 7996694 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7935. Min Act: -0.1700
Data Index: 6832365 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8360718 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7622. Min Act: -0.1700
Data Index: 3835717 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8571062 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3247. Min Range: -6.3247
Max Act: 5.7935. Min Act: -0.1700
Data Index: 1178012 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19