Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2325. Min Range: -7.2325
Max Act: 7.2325. Min Act: -0.1700
Data Index: 1437914 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2325. Min Range: -7.2325
Max Act: 7.1075. Min Act: -0.1700
Data Index: 7851989 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2325. Min Range: -7.2325
Max Act: 7.1075. Min Act: -0.1700
Data Index: 7852000 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2325. Min Range: -7.2325
Max Act: 7.0138. Min Act: -0.1700
Data Index: 2195680 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2325. Min Range: -7.2325
Max Act: 7.0138. Min Act: -0.1700
Data Index: 2093582 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.8263. Min Act: -0.1700
Data Index: 3389296 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.8263. Min Act: -0.1700
Data Index: 830116 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7638. Min Act: -0.1700
Data Index: 4019219 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7638. Min Act: -0.1700
Data Index: 1257836 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7638. Min Act: -0.1700
Data Index: 7507308 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7325. Min Act: -0.1700
Data Index: 4822264 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7013. Min Act: -0.1700
Data Index: 3877216 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6700. Min Act: -0.1700
Data Index: 7151480 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6700. Min Act: -0.1700
Data Index: 5465572 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.7013. Min Act: -0.1700
Data Index: 4058273 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6700. Min Act: -0.1700
Data Index: 2954634 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6388. Min Act: -0.1700
Data Index: 6665556 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6388. Min Act: -0.1700
Data Index: 7474681 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6388. Min Act: -0.1700
Data Index: 3825379 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2325. Min Range: -7.2325
Max Act: 6.6075. Min Act: -0.1700
Data Index: 7853857 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19