Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0447. Min Range: -6.0447
Max Act: 6.0447. Min Act: -0.1700
Data Index: 7071670 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.9510. Min Act: -0.1700
Data Index: 6074538 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8885. Min Act: -0.1700
Data Index: 3797410 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8572. Min Act: -0.1700
Data Index: 1469225 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8572. Min Act: -0.1700
Data Index: 8176093 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8260. Min Act: -0.1700
Data Index: 1738810 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8260. Min Act: -0.1700
Data Index: 5257907 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.8260. Min Act: -0.1700
Data Index: 2276132 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 2591053 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 727873 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 7433973 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 4116015 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1332720 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2998745 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7635. Min Act: -0.1700
Data Index: 3038055 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7322. Min Act: -0.1700
Data Index: 7946459 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7635. Min Act: -0.1700
Data Index: 6413504 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7635. Min Act: -0.1700
Data Index: 446873 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2401217 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0447. Min Range: -6.0447
Max Act: 5.7322. Min Act: -0.1700
Data Index: 2730472 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19