Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0113. Min Range: -8.0113
Max Act: 8.0113. Min Act: -0.1700
Data Index: 1347738 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.8238. Min Act: -0.1700
Data Index: 7463412 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.7301. Min Act: -0.1700
Data Index: 736107 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6988. Min Act: -0.1700
Data Index: 1969596 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6988. Min Act: -0.1700
Data Index: 2787493 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6363. Min Act: -0.1700
Data Index: 6249811 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6363. Min Act: -0.1700
Data Index: 8727675 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6051. Min Act: -0.1700
Data Index: 2271763 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.6363. Min Act: -0.1700
Data Index: 4179038 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5738. Min Act: -0.1700
Data Index: 3721656 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5426. Min Act: -0.1700
Data Index: 2291519 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5426. Min Act: -0.1700
Data Index: 4179040 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5426. Min Act: -0.1700
Data Index: 1860155 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5426. Min Act: -0.1700
Data Index: 4175660 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5426. Min Act: -0.1700
Data Index: 4179036 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5113. Min Act: -0.1700
Data Index: 5971334 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.5113. Min Act: -0.1700
Data Index: 70809 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.4801. Min Act: -0.1700
Data Index: 5495725 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.4176. Min Act: -0.1700
Data Index: 1742874 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0113. Min Range: -8.0113
Max Act: 7.4488. Min Act: -0.1700
Data Index: 6433341 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19