Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.9228. Min Act: -0.1700
Data Index: 7791629 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6091670 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6456249 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2733827 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5791. Min Act: -0.1700
Data Index: 6001676 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5791. Min Act: -0.1700
Data Index: 4423603 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5478. Min Act: -0.1700
Data Index: 1232942 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5166. Min Act: -0.1700
Data Index: 1272389 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5166. Min Act: -0.1700
Data Index: 3221881 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5166. Min Act: -0.1700
Data Index: 3059310 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5166. Min Act: -0.1700
Data Index: 8069637 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.5166. Min Act: -0.1700
Data Index: 816016 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4853. Min Act: -0.1700
Data Index: 4693636 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4853. Min Act: -0.1700
Data Index: 3454321 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4853. Min Act: -0.1700
Data Index: 5484344 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4853. Min Act: -0.1700
Data Index: 5542212 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4541. Min Act: -0.1700
Data Index: 4986505 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4541. Min Act: -0.1700
Data Index: 2872841 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4853. Min Act: -0.1700
Data Index: 3878964 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9228. Min Range: -5.9228
Max Act: 5.4541. Min Act: -0.1700
Data Index: 5074547 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19