Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.6537. Min Act: -0.1696
Data Index: 2015692 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5840. Min Act: -0.1696
Data Index: 3207715 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5752. Min Act: -0.1700
Data Index: 1493554 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5665. Min Act: -0.1698
Data Index: 6168815 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5665. Min Act: -0.1676
Data Index: 8245661 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5577. Min Act: -0.1700
Data Index: 2835410 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5402. Min Act: -0.1693
Data Index: 3100938 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5227. Min Act: -0.1699
Data Index: 5493299 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5139. Min Act: -0.1690
Data Index: 1355904 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5227. Min Act: -0.1700
Data Index: 7662617 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5227. Min Act: -0.1627
Data Index: 429465 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5227. Min Act: -0.1697
Data Index: 4879459 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5139. Min Act: -0.1700
Data Index: 8740765 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1700
Data Index: 651191 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5139. Min Act: -0.1679
Data Index: 2288048 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1695
Data Index: 8740340 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1698
Data Index: 3641824 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1667
Data Index: 4379789 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1692
Data Index: 6468120 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6537. Min Range: -1.6537
Max Act: 1.5051. Min Act: -0.1698
Data Index: 5658965 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19