Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4326 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.2896. Min Act: -0.1700
Data Index: 4684036 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.2583. Min Act: -0.1700
Data Index: 4414492 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.1958. Min Act: -0.1700
Data Index: 6212481 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.1021. Min Act: -0.1700
Data Index: 3658200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.1021. Min Act: -0.1700
Data Index: 7109291 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.0708. Min Act: -0.1700
Data Index: 5209750 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.0708. Min Act: -0.1700
Data Index: 6839945 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.0708. Min Act: -0.1700
Data Index: 4414491 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2896. Min Range: -4.2896
Max Act: 4.0396. Min Act: -0.1700
Data Index: 26502 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9770. Min Act: -0.1700
Data Index: 3366627 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9770. Min Act: -0.1700
Data Index: 7063432 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9458. Min Act: -0.1700
Data Index: 3111511 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9770. Min Act: -0.1700
Data Index: 356997 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9458. Min Act: -0.1700
Data Index: 7999706 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9458. Min Act: -0.1700
Data Index: 2360345 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9458. Min Act: -0.1700
Data Index: 4684035 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9145. Min Act: -0.1700
Data Index: 6212480 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.9145. Min Act: -0.1700
Data Index: 2394259 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.8832. Min Act: -0.1700
Data Index: 7118054 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2896. Min Range: -4.2896
Max Act: 3.8520. Min Act: -0.1700
Data Index: 7156020 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19