Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4384 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4990. Min Act: -0.1700
Data Index: 8819101 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4677. Min Act: -0.1700
Data Index: 1565288 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4365. Min Act: -0.1700
Data Index: 5237296 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4052. Min Act: -0.1700
Data Index: 4511610 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.3427. Min Act: -0.1700
Data Index: 4690472 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.3115. Min Act: -0.1700
Data Index: 3684726 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.3115. Min Act: -0.1700
Data Index: 439804 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.2802. Min Act: -0.1700
Data Index: 8819098 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.2490. Min Act: -0.1700
Data Index: 2853177 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.2177. Min Act: -0.1700
Data Index: 2774821 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.2177. Min Act: -0.1700
Data Index: 4770105 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1865. Min Act: -0.1700
Data Index: 1181114 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 235075 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1865. Min Act: -0.1700
Data Index: 7601520 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 2808356 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 2676640 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 4920696 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 7602231 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1552. Min Act: -0.1700
Data Index: 1405504 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.1240. Min Act: -0.1700
Data Index: 2000995 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19