Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0777. Min Range: -5.0777
Max Act: 5.0777. Min Act: -0.1700
Data Index: 6732465 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.9215. Min Act: -0.1700
Data Index: 1635306 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.8590. Min Act: -0.1700
Data Index: 1871852 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.8277. Min Act: -0.1700
Data Index: 1805568 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.7965. Min Act: -0.1700
Data Index: 1146867 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.7965. Min Act: -0.1700
Data Index: 3674533 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.7652. Min Act: -0.1700
Data Index: 3142907 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6715. Min Act: -0.1700
Data Index: 4900504 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.7027. Min Act: -0.1700
Data Index: 4455488 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6402. Min Act: -0.1700
Data Index: 8598824 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6715. Min Act: -0.1700
Data Index: 257503 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.7027. Min Act: -0.1700
Data Index: 1860931 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6402. Min Act: -0.1700
Data Index: 3745874 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6402. Min Act: -0.1700
Data Index: 531047 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6402. Min Act: -0.1700
Data Index: 7200966 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6090. Min Act: -0.1700
Data Index: 6706494 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.6090. Min Act: -0.1700
Data Index: 6737748 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.5777. Min Act: -0.1700
Data Index: 4807544 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.5777. Min Act: -0.1700
Data Index: 6774314 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0777. Min Range: -5.0777
Max Act: 4.5777. Min Act: -0.1700
Data Index: 1242838 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19