Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2007 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0103. Min Range: -5.0103
Max Act: 5.0103. Min Act: -0.1700
Data Index: 7843239 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9478. Min Act: -0.1700
Data Index: 318534 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9478. Min Act: -0.1700
Data Index: 2687276 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9790. Min Act: -0.1700
Data Index: 2169534 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9165. Min Act: -0.1700
Data Index: 6762981 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9165. Min Act: -0.1700
Data Index: 1146006 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9165. Min Act: -0.1700
Data Index: 3719518 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.9165. Min Act: -0.1700
Data Index: 147594 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8853. Min Act: -0.1700
Data Index: 5824011 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8853. Min Act: -0.1700
Data Index: 6297430 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8540. Min Act: -0.1700
Data Index: 7874558 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8540. Min Act: -0.1700
Data Index: 4955113 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8540. Min Act: -0.1700
Data Index: 5359576 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8228. Min Act: -0.1700
Data Index: 8798755 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8228. Min Act: -0.1700
Data Index: 1340399 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8228. Min Act: -0.1700
Data Index: 4289738 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.7915. Min Act: -0.1700
Data Index: 147592 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8228. Min Act: -0.1700
Data Index: 2050760 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.8228. Min Act: -0.1700
Data Index: 4142516 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0103. Min Range: -5.0103
Max Act: 4.7915. Min Act: -0.1700
Data Index: 4476787 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19