Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.1834. Min Act: -0.1700
Data Index: 733101 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.1209. Min Act: -0.1700
Data Index: 6315454 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.0896. Min Act: -0.1700
Data Index: 7376005 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.0583. Min Act: -0.1700
Data Index: 4064316 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.0583. Min Act: -0.1700
Data Index: 8637425 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1834. Min Range: -4.1834
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5869080 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9958. Min Act: -0.1700
Data Index: 3721609 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9958. Min Act: -0.1700
Data Index: 5419625 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9958. Min Act: -0.1700
Data Index: 8484722 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 2972175 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 931376 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 6855529 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 8795335 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 8775028 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 2166740 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7170554 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9333. Min Act: -0.1700
Data Index: 3290482 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9333. Min Act: -0.1700
Data Index: 7022846 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9333. Min Act: -0.1700
Data Index: 3943180 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1834. Min Range: -4.1834
Max Act: 3.9333. Min Act: -0.1700
Data Index: 5025041 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19