Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 304 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6202. Min Range: -6.6202
Max Act: 6.6202. Min Act: -0.1700
Data Index: 1301854 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6202. Min Range: -6.6202
Max Act: 6.2452. Min Act: -0.1700
Data Index: 883167 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6202. Min Range: -6.6202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 6528519 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.9327. Min Act: -0.1700
Data Index: 787551 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.9015. Min Act: -0.1700
Data Index: 4623248 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.8702. Min Act: -0.1700
Data Index: 2791003 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.8077. Min Act: -0.1700
Data Index: 5636296 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.7765. Min Act: -0.1700
Data Index: 2113425 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.7140. Min Act: -0.1700
Data Index: 3715617 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5554665 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6827. Min Act: -0.1700
Data Index: 1486806 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6468887 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6515. Min Act: -0.1700
Data Index: 2019573 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 305717 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 5157310 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 1001442 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 2773788 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 1955486 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6855568 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6202. Min Range: -6.6202
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4232800 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19