Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1238. Min Range: -5.1238
Max Act: 5.1238. Min Act: -0.1700
Data Index: 3317127 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1238. Min Range: -5.1238
Max Act: 5.0613. Min Act: -0.1700
Data Index: 1247719 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.9988. Min Act: -0.1700
Data Index: 3175969 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2673723 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.9051. Min Act: -0.1700
Data Index: 2879588 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8738. Min Act: -0.1700
Data Index: 8663632 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8738. Min Act: -0.1700
Data Index: 8663626 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1953644 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8426. Min Act: -0.1700
Data Index: 1953643 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8113. Min Act: -0.1700
Data Index: 5622751 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8426. Min Act: -0.1700
Data Index: 1794657 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8113. Min Act: -0.1700
Data Index: 5960299 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8113. Min Act: -0.1700
Data Index: 6140631 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 5426474 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 6084167 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 4856544 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 4747763 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.8113. Min Act: -0.1700
Data Index: 6749013 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 54472 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1238. Min Range: -5.1238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 88005 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19