Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3065. Min Range: -4.3065
Max Act: 4.3065. Min Act: -0.1700
Data Index: 5147798 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3065. Min Range: -4.3065
Max Act: 4.0564. Min Act: -0.1700
Data Index: 6746620 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3065. Min Range: -4.3065
Max Act: 4.0564. Min Act: -0.1700
Data Index: 786605 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3065. Min Range: -4.3065
Max Act: 4.0252. Min Act: -0.1700
Data Index: 6218700 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9627. Min Act: -0.1700
Data Index: 4647906 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9627. Min Act: -0.1700
Data Index: 3786497 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 8356102 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 4246345 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 6018884 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 3829616 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 3579050 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 2259383 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9314. Min Act: -0.1700
Data Index: 5141470 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9627. Min Act: -0.1700
Data Index: 7989156 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9001. Min Act: -0.1700
Data Index: 3910974 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9001. Min Act: -0.1700
Data Index: 111785 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.8689. Min Act: -0.1700
Data Index: 3573072 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.9001. Min Act: -0.1700
Data Index: 960283 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.8689. Min Act: -0.1700
Data Index: 2785746 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3065. Min Range: -4.3065
Max Act: 3.8689. Min Act: -0.1700
Data Index: 7650259 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19