Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.6579. Min Act: -0.1700
Data Index: 6449609 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.6266. Min Act: -0.1700
Data Index: 6371445 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4491437 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.5641. Min Act: -0.1700
Data Index: 2104153 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.5329. Min Act: -0.1700
Data Index: 3735750 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.5016. Min Act: -0.1689
Data Index: 212833 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.5016. Min Act: -0.1696
Data Index: 1123100 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4704. Min Act: -0.1700
Data Index: 594324 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4704. Min Act: -0.1700
Data Index: 4980795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 6393343 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 4656547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 8548297 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 7003509 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 2883879 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4079. Min Act: -0.1700
Data Index: 4744211 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4704. Min Act: -0.1700
Data Index: 2104154 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4391. Min Act: -0.1700
Data Index: 594323 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4079. Min Act: -0.1700
Data Index: 4512664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4079. Min Act: -0.1700
Data Index: 3177481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6579. Min Range: -5.6579
Max Act: 5.4079. Min Act: -0.1700
Data Index: 3401891 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19