Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.5963. Min Act: -0.1700
Data Index: 4648061 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.2213. Min Act: -0.1700
Data Index: 5406590 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.2213. Min Act: -0.1700
Data Index: 171082 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.0963. Min Act: -0.1700
Data Index: 7678362 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.0963. Min Act: -0.1700
Data Index: 5743193 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.0338. Min Act: -0.1700
Data Index: 5406591 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.0338. Min Act: -0.1700
Data Index: 4341481 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5963. Min Range: -8.5963
Max Act: 8.0338. Min Act: -0.1700
Data Index: 171086 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.9713. Min Act: -0.1700
Data Index: 8045633 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.9088. Min Act: -0.1700
Data Index: 4341478 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.9088. Min Act: -0.1700
Data Index: 6905200 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.9713. Min Act: -0.1700
Data Index: 4341476 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.9088. Min Act: -0.1700
Data Index: 8709596 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7838. Min Act: -0.1700
Data Index: 5828128 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7213. Min Act: -0.1700
Data Index: 3291918 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7213. Min Act: -0.1700
Data Index: 2859839 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7213. Min Act: -0.1700
Data Index: 2099622 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7213. Min Act: -0.1700
Data Index: 345695 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.6588. Min Act: -0.1700
Data Index: 7030671 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5963. Min Range: -8.5963
Max Act: 7.7213. Min Act: -0.1700
Data Index: 7546464 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19