Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.4717. Min Act: -0.1700
Data Index: 5896795 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.4717. Min Act: -0.1700
Data Index: 6812318 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.4404. Min Act: -0.1700
Data Index: 188186 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.4092. Min Act: -0.1700
Data Index: 1861063 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.3154. Min Act: -0.1700
Data Index: 4418033 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.2842. Min Act: -0.1700
Data Index: 4950175 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.3154. Min Act: -0.1700
Data Index: 4396511 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.3154. Min Act: -0.1700
Data Index: 3260974 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5654677 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.2217. Min Act: -0.1700
Data Index: 925492 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.2217. Min Act: -0.1700
Data Index: 2117560 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.2217. Min Act: -0.1700
Data Index: 7464507 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1904. Min Act: -0.1700
Data Index: 3681011 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1904. Min Act: -0.1700
Data Index: 878702 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1904. Min Act: -0.1700
Data Index: 6449173 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1592. Min Act: -0.1700
Data Index: 4128908 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5607571 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1592. Min Act: -0.1700
Data Index: 73123 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1279. Min Act: -0.1700
Data Index: 7732612 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4717. Min Range: -5.4717
Max Act: 5.1592. Min Act: -0.1700
Data Index: 2131645 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19