Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.1696. Min Act: -0.1700
Data Index: 2961664 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.1071. Min Act: -0.1700
Data Index: 5006900 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.0446. Min Act: -0.1700
Data Index: 3305869 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.0758. Min Act: -0.1700
Data Index: 2214026 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.0758. Min Act: -0.1700
Data Index: 6925813 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1696. Min Range: -4.1696
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6847198 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9508. Min Act: -0.1700
Data Index: 2001290 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9820. Min Act: -0.1700
Data Index: 8304098 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2474273 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2561895 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9508. Min Act: -0.1700
Data Index: 502760 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9508. Min Act: -0.1700
Data Index: 7772987 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9508. Min Act: -0.1700
Data Index: 8039499 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9508. Min Act: -0.1700
Data Index: 1509779 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.8882. Min Act: -0.1700
Data Index: 5635890 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9195. Min Act: -0.1700
Data Index: 8709306 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9195. Min Act: -0.1700
Data Index: 3594993 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9195. Min Act: -0.1700
Data Index: 5007443 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.8882. Min Act: -0.1700
Data Index: 1545835 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1696. Min Range: -4.1696
Max Act: 3.9195. Min Act: -0.1700
Data Index: 2001291 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19