Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1103 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9728. Min Act: -0.1700
Data Index: 4752732 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9728. Min Act: -0.1700
Data Index: 2005093 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9728. Min Act: -0.1700
Data Index: 5921888 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9728. Min Act: -0.1700
Data Index: 3665443 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 4925226 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 5879881 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 2192492 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 251511 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 4855365 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 6055302 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 1630135 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 2640408 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 6758241 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 8636015 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 1692157 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 3128575 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9416. Min Act: -0.1700
Data Index: 3333904 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 471257 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 4253344 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9103. Min Act: -0.1700
Data Index: 4425911 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19