Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.6653. Min Act: -0.1700
Data Index: 7495789 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.6028. Min Act: -0.1700
Data Index: 7518906 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.5716. Min Act: -0.1700
Data Index: 5453905 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.5403. Min Act: -0.1700
Data Index: 3859935 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4778. Min Act: -0.1700
Data Index: 6890567 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4778. Min Act: -0.1700
Data Index: 4704312 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4466. Min Act: -0.1700
Data Index: 2601494 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4466. Min Act: -0.1700
Data Index: 8300452 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4153. Min Act: -0.1700
Data Index: 1479216 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4153. Min Act: -0.1700
Data Index: 170075 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4153. Min Act: -0.1700
Data Index: 80370 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4153. Min Act: -0.1700
Data Index: 5664323 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.4153. Min Act: -0.1700
Data Index: 6508976 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.3528. Min Act: -0.1700
Data Index: 4916195 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.3528. Min Act: -0.1700
Data Index: 5805804 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.3216. Min Act: -0.1700
Data Index: 7234341 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.2903. Min Act: -0.1700
Data Index: 2566956 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.2591. Min Act: -0.1700
Data Index: 444976 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.2903. Min Act: -0.1700
Data Index: 2130547 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6653. Min Range: -4.6653
Max Act: 4.2278. Min Act: -0.1700
Data Index: 736510 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19