Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.5238. Min Act: -0.1700
Data Index: 6983432 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.4613. Min Act: -0.1700
Data Index: 877306 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.4613. Min Act: -0.1700
Data Index: 2794763 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.3988. Min Act: -0.1700
Data Index: 1687103 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.2113. Min Act: -0.1700
Data Index: 564391 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.2113. Min Act: -0.1693
Data Index: 158084 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.1488. Min Act: -0.1652
Data Index: 7910742 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.0863. Min Act: -0.1700
Data Index: 6154753 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.0863. Min Act: -0.1700
Data Index: 6651475 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.0863. Min Act: -0.1699
Data Index: 8375198 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.0863. Min Act: -0.1700
Data Index: 7693988 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5238. Min Range: -9.5238
Max Act: 9.0863. Min Act: -0.1700
Data Index: 4679480 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.9613. Min Act: -0.1700
Data Index: 147145 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.9613. Min Act: -0.1700
Data Index: 5655389 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8988. Min Act: -0.1694
Data Index: 3188312 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8988. Min Act: -0.1700
Data Index: 3125877 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8988. Min Act: -0.1700
Data Index: 4800816 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8363. Min Act: -0.1700
Data Index: 5002858 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8363. Min Act: -0.1696
Data Index: 5002859 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5238. Min Range: -9.5238
Max Act: 8.8363. Min Act: -0.1700
Data Index: 5652878 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19