Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.9053. Min Act: -0.1700
Data Index: 213639 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.4991. Min Act: -0.1700
Data Index: 5668771 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.3741. Min Act: -0.1700
Data Index: 848441 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.3428. Min Act: -0.1700
Data Index: 8570007 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.3741. Min Act: -0.1700
Data Index: 5344338 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.3116. Min Act: -0.1700
Data Index: 8043283 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2491. Min Act: -0.1700
Data Index: 2774908 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2491. Min Act: -0.1700
Data Index: 6169629 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2178. Min Act: -0.1700
Data Index: 1910410 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2178. Min Act: -0.1700
Data Index: 7503869 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2491. Min Act: -0.1700
Data Index: 1631760 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2491. Min Act: -0.1700
Data Index: 3731642 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2178. Min Act: -0.1700
Data Index: 6169632 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2178. Min Act: -0.1700
Data Index: 1631763 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1866. Min Act: -0.1700
Data Index: 573363 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1866. Min Act: -0.1700
Data Index: 7730281 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1553. Min Act: -0.1700
Data Index: 858332 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1241. Min Act: -0.1700
Data Index: 4661636 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1241. Min Act: -0.1700
Data Index: 1787101 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1241. Min Act: -0.1700
Data Index: 3322637 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19