Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.8056. Min Act: -0.1700
Data Index: 80748 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8406018 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7587. Min Act: -0.1700
Data Index: 6836058 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7274. Min Act: -0.1700
Data Index: 1279068 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7274. Min Act: -0.1700
Data Index: 8105349 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7118. Min Act: -0.1700
Data Index: 7471408 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7274. Min Act: -0.1700
Data Index: 8051967 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7118. Min Act: -0.1700
Data Index: 2407962 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7274. Min Act: -0.1700
Data Index: 5309295 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.7118. Min Act: -0.1700
Data Index: 6431424 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6648. Min Act: -0.1700
Data Index: 6109112 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6805. Min Act: -0.1700
Data Index: 1621950 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6492. Min Act: -0.1700
Data Index: 2960935 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6648. Min Act: -0.1700
Data Index: 8074244 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6336. Min Act: -0.1700
Data Index: 1190542 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6336. Min Act: -0.1700
Data Index: 2241104 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6023. Min Act: -0.1700
Data Index: 7981122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.6336. Min Act: -0.1700
Data Index: 3138732 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.5866. Min Act: -0.1700
Data Index: 1227537 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8056. Min Range: -3.8056
Max Act: 3.5709. Min Act: -0.1700
Data Index: 6010903 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19