Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0487. Min Range: -5.0487
Max Act: 5.0487. Min Act: -0.1700
Data Index: 7955598 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0487. Min Range: -5.0487
Max Act: 5.0487. Min Act: -0.1700
Data Index: 7358287 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0487. Min Range: -5.0487
Max Act: 5.0174. Min Act: -0.1700
Data Index: 834597 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.9862. Min Act: -0.1700
Data Index: 1694634 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 3051778 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.8924. Min Act: -0.1700
Data Index: 4151908 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.8612. Min Act: -0.1700
Data Index: 1104260 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.8612. Min Act: -0.1700
Data Index: 7024365 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7674. Min Act: -0.1700
Data Index: 7089631 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7674. Min Act: -0.1700
Data Index: 4600688 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7674. Min Act: -0.1700
Data Index: 6897448 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7674. Min Act: -0.1700
Data Index: 5850756 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7987. Min Act: -0.1700
Data Index: 5617373 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7362. Min Act: -0.1700
Data Index: 7935009 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7362. Min Act: -0.1700
Data Index: 6254834 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1287500 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7049. Min Act: -0.1700
Data Index: 4592925 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1408428 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7049. Min Act: -0.1700
Data Index: 2297331 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0487. Min Range: -5.0487
Max Act: 4.7049. Min Act: -0.1700
Data Index: 4788576 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19