Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5763 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0030. Min Range: -5.0030
Max Act: 5.0030. Min Act: -0.1700
Data Index: 8448570 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0030. Min Range: -5.0030
Max Act: 5.0030. Min Act: -0.1700
Data Index: 8448575 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.9405. Min Act: -0.1700
Data Index: 3217666 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.9405. Min Act: -0.1700
Data Index: 1557082 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.8467. Min Act: -0.1700
Data Index: 5223387 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7842. Min Act: -0.1700
Data Index: 1268074 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7842. Min Act: -0.1700
Data Index: 1025875 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7530. Min Act: -0.1700
Data Index: 2900300 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7530. Min Act: -0.1700
Data Index: 1025863 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7217. Min Act: -0.1700
Data Index: 6373059 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.7217. Min Act: -0.1700
Data Index: 1994898 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6905. Min Act: -0.1700
Data Index: 1994900 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6905. Min Act: -0.1700
Data Index: 2845693 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6592. Min Act: -0.1700
Data Index: 7514927 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6592. Min Act: -0.1700
Data Index: 5220890 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6280. Min Act: -0.1700
Data Index: 6373071 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6280. Min Act: -0.1700
Data Index: 5417468 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.5967. Min Act: -0.1700
Data Index: 5417480 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.5967. Min Act: -0.1700
Data Index: 7514913 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0030. Min Range: -5.0030
Max Act: 4.6280. Min Act: -0.1700
Data Index: 7956085 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19