Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.2490. Min Act: -0.1700
Data Index: 4464645 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.2177. Min Act: -0.1700
Data Index: 6824300 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.2177. Min Act: -0.1700
Data Index: 5915290 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1865. Min Act: -0.1700
Data Index: 4676709 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1552. Min Act: -0.1700
Data Index: 7944526 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1552. Min Act: -0.1700
Data Index: 4676710 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1240. Min Act: -0.1700
Data Index: 6824292 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1240. Min Act: -0.1700
Data Index: 1551739 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.1240. Min Act: -0.1700
Data Index: 5107001 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0927. Min Act: -0.1700
Data Index: 5512716 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0302. Min Act: -0.1700
Data Index: 4923176 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0615. Min Act: -0.1700
Data Index: 13040 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0615. Min Act: -0.1700
Data Index: 4200368 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0302. Min Act: -0.1700
Data Index: 4933434 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0302. Min Act: -0.1700
Data Index: 5106152 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2490. Min Range: -5.2490
Max Act: 5.0302. Min Act: -0.1700
Data Index: 6053625 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9677. Min Act: -0.1700
Data Index: 4582518 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9677. Min Act: -0.1700
Data Index: 4923175 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9990. Min Act: -0.1700
Data Index: 2250784 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2490. Min Range: -5.2490
Max Act: 4.9677. Min Act: -0.1700
Data Index: 5899214 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19