Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.5611. Min Act: -0.1700
Data Index: 3214579 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.5299. Min Act: -0.1700
Data Index: 3008242 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4674. Min Act: -0.1700
Data Index: 5085572 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4986. Min Act: -0.1700
Data Index: 8504988 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4986. Min Act: -0.1700
Data Index: 8736468 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4674. Min Act: -0.1700
Data Index: 7400830 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4674. Min Act: -0.1700
Data Index: 1632937 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4361. Min Act: -0.1700
Data Index: 368465 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4049. Min Act: -0.1700
Data Index: 693492 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3608770 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.3736. Min Act: -0.1700
Data Index: 228780 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3035334 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.3424. Min Act: -0.1700
Data Index: 2362254 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.3424. Min Act: -0.1700
Data Index: 4526492 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.2799. Min Act: -0.1700
Data Index: 4572110 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.2799. Min Act: -0.1700
Data Index: 5267901 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.2486. Min Act: -0.1700
Data Index: 1662032 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.2174. Min Act: -0.1700
Data Index: 7584837 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.1861. Min Act: -0.1700
Data Index: 3430489 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5611. Min Range: -6.5611
Max Act: 6.1549. Min Act: -0.1700
Data Index: 6019647 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19