Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3415. Min Range: -5.3415
Max Act: 5.3415. Min Act: -0.1700
Data Index: 8652767 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3415. Min Range: -5.3415
Max Act: 5.1853. Min Act: -0.1700
Data Index: 6754331 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3415. Min Range: -5.3415
Max Act: 5.1228. Min Act: -0.1700
Data Index: 5678943 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3415. Min Range: -5.3415
Max Act: 5.0915. Min Act: -0.1700
Data Index: 1839667 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3415. Min Range: -5.3415
Max Act: 5.0603. Min Act: -0.1700
Data Index: 5474073 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9665. Min Act: -0.1700
Data Index: 3191399 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9978. Min Act: -0.1700
Data Index: 5005159 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9978. Min Act: -0.1700
Data Index: 2143459 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9040. Min Act: -0.1700
Data Index: 1443208 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 7310642 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 5037178 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 3729026 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 4756242 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 723871 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2423600 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9040. Min Act: -0.1700
Data Index: 5535196 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 7218830 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.9353. Min Act: -0.1700
Data Index: 673178 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.8728. Min Act: -0.1700
Data Index: 1465081 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3415. Min Range: -5.3415
Max Act: 4.8728. Min Act: -0.1700
Data Index: 8263075 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19