Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0502. Min Range: -4.0502
Max Act: 4.0502. Min Act: -0.1700
Data Index: 555820 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.9877. Min Act: -0.1700
Data Index: 5366038 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8939. Min Act: -0.1700
Data Index: 8088568 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.9252. Min Act: -0.1700
Data Index: 84919 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8939. Min Act: -0.1700
Data Index: 5312700 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8627. Min Act: -0.1700
Data Index: 8195293 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8627. Min Act: -0.1700
Data Index: 538569 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8627. Min Act: -0.1700
Data Index: 5910946 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8001. Min Act: -0.1700
Data Index: 7084772 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8001. Min Act: -0.1700
Data Index: 1092253 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8001. Min Act: -0.1700
Data Index: 3783835 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8001. Min Act: -0.1700
Data Index: 2672201 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7688. Min Act: -0.1700
Data Index: 3224477 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7688. Min Act: -0.1700
Data Index: 1441816 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.8001. Min Act: -0.1700
Data Index: 5107047 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7376. Min Act: -0.1700
Data Index: 611723 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7376. Min Act: -0.1700
Data Index: 7299386 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7376. Min Act: -0.1700
Data Index: 1633409 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7376. Min Act: -0.1700
Data Index: 5512198 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0502. Min Range: -4.0502
Max Act: 3.7688. Min Act: -0.1700
Data Index: 4175745 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19