Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2290. Min Range: -6.2290
Max Act: 6.2290. Min Act: -0.1700
Data Index: 6149068 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.6665. Min Act: -0.1700
Data Index: 2105989 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.5415. Min Act: -0.1700
Data Index: 8298577 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.5102. Min Act: -0.1700
Data Index: 5317571 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4790. Min Act: -0.1700
Data Index: 5695461 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4477. Min Act: -0.1700
Data Index: 4157016 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4477. Min Act: -0.1700
Data Index: 2137229 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4477. Min Act: -0.1700
Data Index: 4908625 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4165. Min Act: -0.1700
Data Index: 1915655 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.4165. Min Act: -0.1700
Data Index: 8823301 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3852. Min Act: -0.1700
Data Index: 6095020 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3852. Min Act: -0.1700
Data Index: 4710190 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3852. Min Act: -0.1700
Data Index: 3679849 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3540. Min Act: -0.1700
Data Index: 5307562 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3540. Min Act: -0.1700
Data Index: 3799882 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3540. Min Act: -0.1700
Data Index: 6862358 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3540. Min Act: -0.1700
Data Index: 1351341 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3540. Min Act: -0.1700
Data Index: 1506326 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.3227. Min Act: -0.1700
Data Index: 288007 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2290. Min Range: -6.2290
Max Act: 5.2915. Min Act: -0.1700
Data Index: 4164748 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19