Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.3127. Min Act: -0.1700
Data Index: 5478519 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.2814. Min Act: -0.1700
Data Index: 3467120 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.2502. Min Act: -0.1700
Data Index: 14429 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.2814. Min Act: -0.1700
Data Index: 6782870 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1877. Min Act: -0.1700
Data Index: 5586830 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.2189. Min Act: -0.1700
Data Index: 7145918 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1564. Min Act: -0.1700
Data Index: 5543486 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.2189. Min Act: -0.1700
Data Index: 3683230 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1877. Min Act: -0.1700
Data Index: 8623348 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1564. Min Act: -0.1700
Data Index: 4117011 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1877. Min Act: -0.1700
Data Index: 4693955 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1564. Min Act: -0.1700
Data Index: 8591037 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1564. Min Act: -0.1700
Data Index: 167353 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1252. Min Act: -0.1700
Data Index: 4206743 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1252. Min Act: -0.1700
Data Index: 7820832 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1252. Min Act: -0.1700
Data Index: 6313543 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1252. Min Act: -0.1700
Data Index: 8078581 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.1252. Min Act: -0.1700
Data Index: 1779793 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.0627. Min Act: -0.1700
Data Index: 3522959 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3127. Min Range: -6.3127
Max Act: 6.0627. Min Act: -0.1700
Data Index: 6725738 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19